© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29279
    Prev
    Next
    INDEX
    Explanations

    string and character manipulation

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

    string manipulation, slicing, substrings

    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
     زا
    0.49
    資金
    0.48
     રાહ
    0.47
    錐
    0.46
    เงิน
    0.46
    探し
    0.45
     datap
    0.45
    𒉣
    0.44
    fiscal
    0.44
    财政
    0.44
    POSITIVE LOGITS
    字符
    1.07
    字符串
    1.03
     String
    0.95
    Substring
    0.91
     strlen
    0.89
    StringType
    0.89
    String
    0.88
     Characters
    0.88
     substring
    0.87
    CharArray
    0.87
    Activations Density 0.005%

    No Known Activations