© 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. 53968
    Prev
    Next
    INDEX
    Explanations

    use as explanation or function

    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
    ssohn
    -0.98
     some
    -0.91
    cknow
    -0.90
     useStyles
    -0.88
     gema
    -0.85
    厳選
    -0.84
     cilindro
    -0.83
     XXXI
    -0.83
     Kone
    -0.82
     teatr
    -0.82
    POSITIVE LOGITS
     replacement
    1.84
     substitute
    1.66
     replacements
    1.52
     basis
    1.49
    replacement
    1.29
     standalone
    1.28
     part
    1.27
     reemplazo
    1.25
     tool
    1.24
     replace
    1.24
    Activations Density 0.108%

    No Known Activations