© 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. 355
    Prev
    Next
    INDEX
    Explanations

    code syntax, file extensions, yaml, json

    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
    땃
    -1.49
    somewhat
    -1.41
     páns
    -1.38
     besos
    -1.38
    だけではなく
    -1.36
    colorful
    -1.35
     akci
    -1.34
     ſi
    -1.31
     esportivo
    -1.30
     dáms
    -1.28
    POSITIVE LOGITS
     now
    1.23
     when
    1.20
     every
    1.17
    the
    1.14
     on
    1.13
     after
    1.10
     start
    1.06
    ….
    1.05
     take
    1.05
     only
    1.05
    Activations Density 0.017%

    No Known Activations