© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98322
    Prev
    Next
    INDEX
    Explanations

    string startsWith endsWith replace substring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTCF
    -0.86
    Люди
    -0.85
    owiak
    -0.84
     ngào
    -0.83
    ifolia
    -0.79
    тием
    -0.79
    nock
    -0.77
    瘙
    -0.77
     Virtu
    -0.76
     gouache
    -0.76
    POSITIVE LOGITS
     replace
    1.08
     substr
    1.02
     char
    1.02
     substring
    1.02
    Starts
    0.96
    endswith
    0.96
    substring
    0.95
    replace
    0.92
     Char
    0.89
     reverse
    0.89
    Activations Density 0.077%

    No Known Activations