© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16364
    Prev
    Next
    INDEX
    Explanations

    duration and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     கூறியுள்ளார்
    0.53
     propellant
    0.50
    anon
    0.50
    txt
    0.49
    Highlight
    0.49
    ක්ෂ
    0.49
    6
    0.48
     年度
    0.48
     denies
    0.47
    ques
    0.47
    POSITIVE LOGITS
     beetje
    0.59
     admittedly
    0.57
     лучших
    0.57
     но
    0.55
    肚
    0.55
    <unused2131>
    0.55
     милли
    0.55
     गिनती
    0.55
    連續
    0.54
    <unused742>
    0.54
    Activations Density 0.000%

    No Known Activations