© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212669
    Prev
    Next
    INDEX
    Explanations

    currency and crime values

    np_acts-logits-general · gemini-2.5-flash-lite

    legal and ethical issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    গিরই
    0.47
    chyné
    0.44
     operandSize
    0.42
    شتغل
    0.41
     Decedent
    0.41
    ത്തിറ
    0.41
     Erwachsene
    0.41
    널
    0.41
    圄
    0.41
    領導
    0.40
    POSITIVE LOGITS
    crime
    0.61
    =
    0.60
     =
    0.57
    ES
    0.56
     -
    0.55
     defra
    0.55
     bank
    0.55
    ZZ
    0.54
     of
    0.52
    dup
    0.52
    Activations Density 0.002%

    No Known Activations