© 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. 30969
    Prev
    Next
    INDEX
    Explanations

    boolean false

    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
     subtracted
    0.46
     Removed
    0.44
     $$\
    0.44
     Throw
    0.43
     REPRESENT
    0.43
    久
    0.43
     CONTINUE
    0.43
    ᡵ
    0.42
     Subtract
    0.42
     Remover
    0.42
    POSITIVE LOGITS
    s
    0.44
     أي
    0.43
     bewusst
    0.42
     الحم
    0.42
     مهما
    0.40
     situ
    0.40
     butt
    0.38
     الهم
    0.38
     ataque
    0.38
     وير
    0.38
    Activations Density 0.069%

    No Known Activations