© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3143
    Prev
    Next
    INDEX
    Explanations

    code block endings

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

    The neuron fires most strongly on numeric labels or offsets (decimal or integer numbers used like instruction addresses or line‐number annotations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    hashCode
    0.55
     ));
    0.55
     */;
    0.54
     ]);
    0.52
    UIView
    0.51
     ''),
    0.50
     जाते
    0.50
    printStackTrace
    0.50
     mView
    0.49
    )];
    0.49
    POSITIVE LOGITS
    }
    0.62
    ?}
    0.62
    ࿔
    0.60
    $}
    0.58
    .}
    0.57
     बेहतर
    0.57
    !}
    0.57
    зиден
    0.57
    }:\
    0.57
    Better
    0.56
    Activations Density 0.000%

    No Known Activations