© 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. 116187
    Prev
    Next
    INDEX
    Explanations

    Punycode, studio, family, project, study, table, range, Purana

    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
    জ
    -0.73
    还
    -0.72
     Quinta
    -0.71
     Numerade
    -0.69
    ktory
    -0.69
    wunsch
    -0.66
    假
    -0.66
     uo
    -0.66
    @
    -0.65
     begon
    -0.64
    POSITIVE LOGITS
    ตน
    0.74
    ératures
    0.72
    EIO
    0.66
     files
    0.66
    Accessible
    0.65
     pal
    0.65
    Accession
    0.64
    ≿
    0.64
     nearing
    0.62
    )))));
    0.61
    Activations Density 0.082%

    No Known Activations