© 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. 13245
    Prev
    Next
    INDEX
    Explanations

    "`take you`" or `"by name"`

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

    The neuron flags the single most salient topic word in each segment—typically the head noun or keyword that introduces what that section is about.

    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
    ا
    1.09
     Ме
    0.93
     Л
    0.86
    اكم
    0.85
     тренер
    0.81
    ه‌های
    0.79
     Фі
    0.78
     muscul
    0.76
     pcMove
    0.75
     Ј
    0.74
    POSITIVE LOGITS
    s
    0.98
    term
    0.89
    werk
    0.86
    mation
    0.84
    r
    0.81
    plus
    0.80
    n
    0.79
    mein
    0.78
    strom
    0.75
    log
    0.75
    Activations Density 0.000%

    No Known Activations