© 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. 86410
    Prev
    Next
    INDEX
    Explanations

    based on data or reference

    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
     in
    -2.08
     there
    -1.48
    tvguide
    -1.44
    affordable
    -1.38
    hoka
    -1.37
    obut
    -1.36
     |
    -1.35
     be
    -1.34
    pirate
    -1.30
     topics
    -1.27
    POSITIVE LOGITS
    ológico
    1.32
     andata
    1.31
    構造
    1.23
    ]$.
    1.23
    stvo
    1.19
     lavabo
    1.17
     vya
    1.16
     greifen
    1.16
    řejmě
    1.16
     karan
    1.16
    Activations Density 0.053%

    No Known Activations