© 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. 100387
    Prev
    Next
    INDEX
    Explanations

    property ownership and description

    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
    From
    -1.84
    мії
    -1.73
            
    -1.70
    7
    -1.69
    }$
    -1.59
     –
    -1.56
    0
    -1.54
    );
    -1.52
    uls
    -1.48
                    
    -1.47
    POSITIVE LOGITS
     to
    1.59
    笃
    1.56
     prácti
    1.55
     antiguas
    1.53
     peoples
    1.52
     skóra
    1.52
    )
    1.47
     راحتی
    1.45
     شما
    1.45
     famosa
    1.44
    Activations Density 0.010%

    No Known Activations