© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12921
    Prev
    Next
    INDEX
    Explanations

    Saint

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     ঢে
    0.63
    IBLE
    0.60
    ój
    0.59
    ರಿನ
    0.57
     penta
    0.56
    เค
    0.56
    携
    0.55
    vertine
    0.55
     stara
    0.55
    ष्मा
    0.54
    POSITIVE LOGITS
     Charles
    0.65
    Charles
    0.64
    Timothy
    0.63
     Timothy
    0.61
     Louis
    0.61
     cloud
    0.59
     Cloud
    0.58
     clouds
    0.56
     ×
    0.56
    Louis
    0.54
    Activations Density 0.018%

    No Known Activations