© 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. 2919
    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
     РФ
    0.64
     জ
    0.58
     ק
    0.55
    -/
    0.55
     Ա
    0.55
    +}$,
    0.55
    ૦
    0.55
    ͈
    0.54
     माजी
    0.53
     смог
    0.53
    POSITIVE LOGITS
     psychotherapy
    0.49
     fantasies
    0.47
     kinds
    0.46
     theologians
    0.46
    iritual
    0.44
     bhikkh
    0.44
     During
    0.44
     things
    0.43
     religious
    0.43
    kind
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.