© 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. 13525
    Prev
    Next
    INDEX
    Explanations

    path to menu

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

    The neuron strongly responds to the genealogy‐style “X begot Y” constructions (i.e. the word “begot” and the adjoining proper names in biblical lineage lists).

    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
     निजामाच्या
    0.57
    ccnc
    0.56
    tavern
    0.54
    ᆢ
    0.52
    chenko
    0.49
    gebäude
    0.49
    vasser
    0.49
    ᾰ
    0.49
     собственной
    0.48
    ᚕ
    0.48
    POSITIVE LOGITS
     });
    0.60
     These
    0.58
    );
    0.54
     Various
    0.50
     Usually
    0.49
     );
    0.48
    });
    0.48
     */
    0.47
            
    0.47
     There
    0.47
    Activations Density 0.001%

    No Known Activations