© 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
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2060
    Prev
    Next
    INDEX
    Explanations

    closing brace or end of declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    0.83
    </h6>
    0.78
     BEAUT
    0.69
     psich
    0.68
     […]
    0.67
     beauty
    0.67
     신경
    0.66
     än
    0.65
     renovación
    0.63
     olla
    0.61
    POSITIVE LOGITS
    }
    4.50
    .}
    4.28
     }
    4.20
    }.
    4.17
    '}
    4.11
    !}
    4.09
    ?}
    4.01
    ,}
    3.95
    };
    3.91
    },
    3.91
    Activations Density 0.240%

    No Known Activations