© 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. 70102
    Prev
    Next
    INDEX
    Explanations

    java technologies like JGit, JHipster, JSF

    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
    atyw
    -0.77
     asked
    -0.75
     PyLong
    -0.70
    詮
    -0.69
     profund
    -0.69
     Nick
    -0.68
    ण्ड
    -0.68
     said
    -0.68
     ask
    -0.67
    krb
    -0.67
    POSITIVE LOGITS
     soot
    0.85
     memanfaatkan
    0.82
    SEX
    0.79
     bint
    0.79
    sified
    0.79
     VALID
    0.79
     javax
    0.79
    коле
    0.78
    profiler
    0.78
    SIE
    0.78
    Activations Density 0.041%

    No Known Activations