© 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-262K
    7. 201888
    Prev
    Next
    INDEX
    Explanations

    choices and statements

    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_262k_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
    df
    0.45
     PASS
    0.44
    LL
    0.43
    LOG
    0.42
    λώ
    0.42
     周
    0.42
    周
    0.42
    rl
    0.42
    tracking
    0.41
     Nag
    0.40
    POSITIVE LOGITS
     Vorteil
    0.43
    ാല്‍
    0.43
    collide
    0.43
     Spacious
    0.42
     berjudul
    0.40
     fuoco
    0.40
     standpoint
    0.40
    ้ํา
    0.40
     Daytime
    0.40
    കള്‍
    0.40
    Activations Density 0.003%

    No Known Activations