© 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. 163392
    Prev
    Next
    INDEX
    Explanations

    beneficial or helpful

    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
     Wonders
    0.42
    ]&
    0.42
     Wilber
    0.41
    บคุม
    0.40
    purple
    0.39
    Juventus
    0.39
     imperialism
    0.39
     adren
    0.39
     굉장
    0.38
    orange
    0.38
    POSITIVE LOGITS
    ственности
    0.48
     μεγ
    0.43
    ках
    0.43
    itores
    0.42
     треуго
    0.42
     хозяй
    0.40
    弁
    0.40
     трех
    0.39
     সাহায্য
    0.39
    теп
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.