© 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. 71004
    Prev
    Next
    INDEX
    Explanations

    words starting with sto

    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
    </td>
    -2.89
    嗞
    -2.72
    
    -2.39
    B
    -2.34
    h
    -2.33
    Is
    -2.30
     sterren
    -2.28
    曁
    -2.28
     pulsante
    -2.28
    quot
    -2.28
    POSITIVE LOGITS
    });
    3.48
    </strong>
    3.38
    ));
    3.06
    };
    2.77
    ();
    2.75
    ).
    2.72
    ”;
    2.61
    ￬
    2.59
    閏
    2.56
    })
    2.39
    Activations Density 0.013%

    No Known Activations