© 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. 203693
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and words

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

    yet untouched

    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
     CT
    0.47
     US
    0.46
     CG
    0.46
     offshore
    0.45
     S
    0.45
     techn
    0.45
     Away
    0.45
     char
    0.44
     Offshore
    0.44
     chem
    0.44
    POSITIVE LOGITS
    𝒶
    0.50
    他也
    0.49
    étricas
    0.48
    Ꮞ
    0.48
    这
    0.47
    吴
    0.47
    她
    0.47
    𝒽
    0.46
    ｭ
    0.46
    這
    0.46
    Activations Density 0.000%

    No Known Activations