© 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. 62299
    Prev
    Next
    INDEX
    Explanations

    no restrictions for use

    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
     writs
    0.49
     cheque
    0.46
     incomes
    0.46
     mastic
    0.45
    한다는
    0.45
     bicovariant
    0.45
     ediyorum
    0.45
    ç
    0.45
     carcinomas
    0.44
     diversion
    0.43
    POSITIVE LOGITS
    Exist
    0.48
    锜
    0.47
    媟
    0.47
    或许
    0.46
    用于
    0.46
    薁
    0.45
    明显
    0.45
     നിറ
    0.44
     আজও
    0.44
    هار
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.