© 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. 105656
    Prev
    Next
    INDEX
    Explanations

    ensure your

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

    metropolitan areauser flow diagrams

    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
    がつ
    0.55
    iftung
    0.52
    urger
    0.51
    ص
    0.50
     च
    0.50
     tut
    0.50
     Β
    0.49
     weeds
    0.49
     Г
    0.49
    bases
    0.48
    POSITIVE LOGITS
     avanti
    0.53
     alguma
    0.47
    貘
    0.46
     Warwick
    0.43
    0.43
     சரியான
    0.42
     Marriott
    0.41
     specialising
    0.41
     quadrados
    0.41
     alumnus
    0.41
    Activations Density 0.000%

    No Known Activations