© 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. 20046
    Prev
    Next
    INDEX
    Explanations

    commentator or sportscaster

    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
     to
    -1.59
    藁
    -1.50
     $
    -1.45
    d
    -1.45
    唖
    -1.44
     be
    -1.39
    ]
    -1.38
     Occasionally
    -1.30
    étant
    -1.27
     allgemein
    -1.26
    POSITIVE LOGITS
     grij
    1.47
     夜景
    1.45
    cloths
    1.43
    lamps
    1.39
    ✋
    1.38
     perfecte
    1.38
    岿
    1.38
     Cik
    1.38
    💦
    1.38
    涐
    1.37
    Activations Density 0.014%

    No Known Activations