© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62878
    Prev
    Next
    INDEX
    Explanations

    percentages of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     большинство
    0.51
     большин
    0.47
     большинстве
    0.44
     ठहरा
    0.43
    銃
    0.43
    bedaan
    0.41
    блема
    0.41
    θυν
    0.41
     forskjellige
    0.40
    ตา
    0.40
    POSITIVE LOGITS
     the
    0.53
     Rangers
    0.51
    total
    0.51
     total
    0.48
     totale
    0.48
    %
    0.45
     Crew
    0.44
     Wird
    0.44
     Kampf
    0.43
    Total
    0.42
    Activations Density 0.039%

    No Known Activations