© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3517
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    棪
    0.81
     adequada
    0.75
    čnog
    0.71
    ফতার
    0.71
    ल्यानंतर
    0.70
     budynku
    0.70
     Vallée
    0.70
    peau
    0.69
    电视台
    0.69
    成立
    0.69
    POSITIVE LOGITS
    на
    0.83
     plays
    0.77
    ان
    0.76
     B
    0.72
    était
    0.70
    が生
    0.66
    about
    0.65
    aient
    0.65
    Sing
    0.65
    enjoy
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.