© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6316
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    ending punctuation or closing delimiter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    </h3>
    0.55
    </h5>
    0.50
     )}
    0.49
     』
    0.48
    ပါတယ်
    0.48
    =""/>
    0.48
    }"/>
    0.46
    }}}
    0.46
     ค่ะ
    0.45
    ,}
    0.44
    POSITIVE LOGITS
    ").
    1.95
     "").
    1.94
    ').
    1.92
     '').
    1.86
    }).
    1.84
    }.
    1.81
    ).
    1.80
    ]).
    1.79
    ()).
    1.79
    '].
    1.77
    Activations Density 0.360%

    No Known Activations