© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3327
    Prev
    Next
    INDEX
    Explanations

    potential negative outcomes of behaviors

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

    This neuron identifies detailed technical descriptions of how a device or sensor operates, especially explanations of measurement principles.

    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_24_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
    -
    0.68
    /
    0.64
     crappy
    0.62
    0.62
    ?
    0.61
     awhile
    0.60
     dast
    0.60
    0
    0.59
    !
    0.57
     heinous
    0.57
    POSITIVE LOGITS
    रिडोर
    0.60
     మరింత
    0.58
     أيضا
    0.57
    पाउंड
    0.57
     অনেকগুলি
    0.56
    бычно
    0.56
     সাধারণত
    0.55
    नावश्यक
    0.55
    ivität
    0.54
     теркәлүсез
    0.54
    Activations Density 0.246%

    No Known Activations