© 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. 33199
    Prev
    Next
    INDEX
    Explanations

    next() or reject()

    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
     знания
    0.40
     ஹெ
    0.40
    🧉
    0.40
    𒁉
    0.39
     बरे
    0.39
     hesitant
    0.38
     मधुर
    0.38
     মিষ্টি
    0.38
     तुझ्या
    0.38
    ﮭ
    0.38
    POSITIVE LOGITS
    cm
    0.53
    ர்த
    0.43
    abez
    0.43
    തെന്ന്
    0.43
    kw
    0.42
    percent
    0.42
    logs
    0.42
    asun
    0.42
    asis
    0.42
    real
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.