© 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. 22971
    Prev
    Next
    INDEX
    Explanations

    preceding emphasis marks

    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
    饽
    0.38
     invo
    0.38
    RENDITION
    0.36
     invoicing
    0.35
    stvo
    0.35
     isAdmin
    0.34
     lenses
    0.34
    ༈
    0.34
     eyewear
    0.34
     వీడియో
    0.34
    POSITIVE LOGITS
    row
    0.39
     võimalik
    0.38
    CB
    0.37
    Au
    0.37
     Prendre
    0.37
    :\
    0.37
    Typ
    0.36
     संतुलित
    0.36
    cod
    0.36
    Cod
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.