© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12166
    Prev
    Next
    INDEX
    Explanations

    crisis hotlines and phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on the numeral “2” when it appears as part of “24” (e.g. in “24/7” or “24 hours a day,” denoting around-the-clock availability).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameValuePair
    0.62
    ОВ
    0.61
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.59
    ]->
    0.58
    ="">
    0.57
    0.57
    acity
    0.57
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.56
    ()->
    0.56
    }=\
    0.55
    POSITIVE LOGITS
     selalu
    0.68
     Kek
    0.61
     tetap
    0.57
     bahis
    0.55
     Komis
    0.54
     bek
    0.53
     interrupt
    0.53
     petal
    0.53
     Glad
    0.52
     carol
    0.52
    Activations Density 0.000%

    No Known Activations