© 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. 2383
    Prev
    Next
    INDEX
    Explanations

    Pew Research

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

    The main thing this neuron does is detect numeric tokens or numerical data (e.g. isolated numbers or measurements).

    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
    0.71
    ).
    0.64
     vibr
    0.63
     geologic
    0.63
    .
    0.62
    作为
    0.59
    ,
    0.59
     precision
    0.59
    ].
    0.57
    ometric
    0.57
    POSITIVE LOGITS
     Amnesty
    0.89
     repentance
    0.88
     blackmail
    0.88
     estranged
    0.86
     apologised
    0.83
     negociación
    0.82
     unauthorised
    0.82
     قتل
    0.82
     পুরনো
    0.81
     перегово
    0.81
    Activations Density 0.749%

    No Known Activations