© 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. 21768
    Prev
    Next
    INDEX
    Explanations

    funeral services

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

    override this risky behavior

    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
     mutta
    0.53
     역
    0.46
     but
    0.46
     Exhibit
    0.45
     Westfield
    0.42
     monetary
    0.42
     jednak
    0.41
    ↵↵
    0.40
     ngunit
    0.40
     tetapi
    0.39
    POSITIVE LOGITS
    gather
    0.49
    early
    0.48
     الجن
    0.45
     மனை
    0.44
    binomial
    0.44
    協會
    0.44
     инфра
    0.43
    ጠ
    0.43
    াঃ
    0.43
    ቺ
    0.43
    Activations Density 0.000%

    No Known Activations