© 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-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 8871
    Prev
    Next
    INDEX
    Explanations

    code structure/syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    ();}
    0.79
    };
    0.72
    ;}
    0.72
    );}
    0.72
    ?}
    0.69
    };\
    0.62
    ";}
    0.61
     };
    0.59
    '};
    0.57
    =}
    0.57
    POSITIVE LOGITS
     EAC
    0.62
     Ã
    0.58
     comple
    0.55
     negatives
    0.54
     Environ
    0.54
     બના
    0.52
     CMOS
    0.52
     faculty
    0.52
    klärung
    0.52
     Nachricht
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.