© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58976
    Prev
    Next
    INDEX
    Explanations

    quite low or limited

    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
    厹
    -2.86
    
    -2.70
    strange
    -2.67
    ৢ
    -2.64
     incorpora
    -2.56
    commonly
    -2.55
     "
    -2.53
    を書く
    -2.52
     vanguardia
    -2.50
    ༷
    -2.47
    POSITIVE LOGITS
    there
    2.84
    Using
    2.78
     Using
    2.67
     facilitates
    2.64
    With
    2.55
    ⇰
    2.55
    Several
    2.53
    他的
    2.45
     demonstrates
    2.45
    ))$_
    2.42
    Activations Density 0.002%

    No Known Activations