© 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. 10534
    Prev
    Next
    INDEX
    Explanations

    knew it/that/I/they

    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
     –
    -1.95
     These
    -1.92
     Interestingly
    -1.79
     Also
    -1.69
    </h3>
    -1.66
    0
    -1.59
    These
    -1.58
    家用
    -1.49
    </strong>
    -1.40
     erwähnten
    -1.37
    POSITIVE LOGITS
     that
    2.14
    ICOLON
    1.85
    
    1.79
    ⢕
    1.73
     your
    1.70
    }>;
    1.68
    aided
    1.66
    犛
    1.63
    ⇹
    1.57
    秾
    1.53
    Activations Density 0.045%

    No Known Activations