© 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. 12-GEMMASCOPE-2-RES-16K
    7. 9610
    Prev
    Next
    INDEX
    Explanations

    Lunch time slot

    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_12_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
    ā
    1.69
    перь
    1.63
    ieniu
    1.58
    SU
    1.53
    LE
    1.52
    ieni
    1.51
    OF
    1.47
    anc
    1.46
     wodurch
    1.43
    에
    1.43
    POSITIVE LOGITS
    <0x80>
    1.63
     credence
    1.32
     Comrade
    1.30
    жды
    1.24
     Rainy
    1.20
     purse
    1.20
     Aspects
    1.17
     Columns
    1.15
     CAGR
    1.14
    ي
    1.14
    Activations Density 0.027%

    No Known Activations