© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108298
    Prev
    Next
    INDEX
    Explanations

    string manipulation methods

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

    The neuron strongly activates on terms related to counting or measuring (e.g. “number,” “characters,” “length,” “vowels,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     wody
    -0.82
     tejto
    -0.77
    órum
    -0.75
    giarism
    -0.74
     ważne
    -0.74
    enames
    -0.73
    Hình
    -0.72
    เอก
    -0.71
    alumno
    -0.71
    Ohio
    -0.71
    POSITIVE LOGITS
     characters
    1.63
    toCharArray
    1.62
     char
    1.48
    chars
    1.47
     strlen
    1.45
     chars
    1.43
    Chars
    1.38
     letters
    1.36
    CharArray
    1.34
    char
    1.30
    Activations Density 0.031%

    No Known Activations