© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3568
    Prev
    Next
    INDEX
    Explanations

    initiating actions or queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     thành
    2.46
     Ү
    2.38
     Veľ
    2.29
    คอม
    2.29
     คอม
    2.25
     című
    2.24
     waxay
    2.24
    図
    2.23
    จ
    2.22
     レン
    2.22
    POSITIVE LOGITS
    ice
    1.14
    ask
    1.06
    4
    1.05
    od
    1.03
    3
    1.03
    6
    1.02
    ot
    1.00
    op
    0.97
    up
    0.97
    5
    0.95
    Activations Density 0.055%

    No Known Activations