© 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. 134698
    Prev
    Next
    INDEX
    Explanations

    verification, rating, achieve excellent

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

    describing human experiences and culture

    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
    ci
    0.49
    <0x0D>
    0.47
     indústria
    0.46
    t
    0.45
    evil
    0.43
    GM
    0.43
     nucleons
    0.42
     दुल्
    0.42
     crucially
    0.41
    فاع
    0.41
    POSITIVE LOGITS
     barro
    0.50
     rangka
    0.49
     kondisi
    0.48
    뢰
    0.47
     задачи
    0.47
    ଟି
    0.46
    ִ
    0.46
     mekanisme
    0.46
     Bedingungen
    0.45
    тельно
    0.45
    Activations Density 0.001%

    No Known Activations