© 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. 101740
    Prev
    Next
    INDEX
    Explanations

    names followed by surnames

    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
     .
    -2.91
    “
    -2.78
    ,"
    -2.66
    }
    -2.63
    on
    -2.48
    ).
    -2.45
     größer
    -2.30
    $
    -2.27
    _{
    -2.22
    ):
    -2.20
    POSITIVE LOGITS
    栳
    2.98
    婞
    2.69
    筇
    2.55
    冧
    2.50
    蛩
    2.47
    
    2.44
    ﮟ
    2.38
            
    2.36
    槇
    2.31
    羕
    2.31
    Activations Density 0.002%

    No Known Activations