© 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. 10-GEMMASCOPE-RES-131K
    7. 13312
    Prev
    Next
    INDEX
    Explanations

    some followed by words

    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_10/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
     or
    -1.63
     which
    -1.49
     this
    -1.49
     partire
    -1.49
     number
    -1.47
    p
    -1.43
    c
    -1.42
    which
    -1.34
    只有一
    -1.34
    ைய
    -1.33
    POSITIVE LOGITS
     gigantes
    1.71
    ⑊
    1.59
    綃
    1.58
     remota
    1.55
    ♰
    1.51
     enormes
    1.47
     oferta
    1.47
     inexist
    1.45
     tremend
    1.45
    across
    1.44
    Activations Density 0.036%

    No Known Activations