© 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. 237128
    Prev
    Next
    INDEX
    Explanations

    insurance considerations

    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
    बंधनाच्या
    0.54
     QuantityOnHand
    0.52
     nirvach
    0.50
    瘍
    0.50
     الکتر
    0.48
     dakkh
    0.48
     thromb
    0.48
     ventric
    0.48
     ঘাঁটি
    0.48
    🎋
    0.47
    POSITIVE LOGITS
    ge
    0.62
    ah
    0.57
    ap
    0.55
    ac
    0.53
    ov
    0.53
    ad
    0.52
    SA
    0.52
    ai
    0.51
    et
    0.50
    ce
    0.50
    Activations Density 0.000%

    No Known Activations