© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2491
    Prev
    Next
    INDEX
    Explanations

    used as AAS

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

    explaining how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ing
    0.66
    not
    0.52
    styles
    0.52
    IN
    0.51
    RI
    0.50
    AC
    0.50
    <0xE3>
    0.48
    Notes
    0.48
    likes
    0.47
    TE
    0.47
    POSITIVE LOGITS
     menjel
    0.59
    ὐ
    0.57
    xcuser
    0.56
     dün
    0.55
     nást
    0.54
     banyak
    0.54
     ног
    0.54
     možné
    0.54
     ferrugineux
    0.54
    өрд
    0.54
    Activations Density 0.000%

    No Known Activations