© 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. 187638
    Prev
    Next
    INDEX
    Explanations

    string and related words

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

    string and strings

    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
    ég
    0.58
    ية
    0.52
    ère
    0.51
    的应用
    0.51
    wig
    0.50
    櫒
    0.50
     информация
    0.49
    渠道
    0.49
    Clients
    0.48
    <0x80>
    0.48
    POSITIVE LOGITS
     string
    1.02
     getString
    1.00
     STRING
    0.83
    string
    0.81
     strung
    0.80
     strings
    0.78
     str
    0.76
    GetString
    0.75
    STRING
    0.73
    文字列
    0.71
    Activations Density 0.042%

    No Known Activations