© 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. 106525
    Prev
    Next
    INDEX
    Explanations

    old and variations

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

    RAID controller

    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
    និច
    0.60
    ังกฤษ
    0.56
     météor
    0.55
    𒊬
    0.55
    हासन
    0.53
     settles
    0.52
     gouttes
    0.52
     ocor
    0.51
     skyrock
    0.51
    ʸ
    0.51
    POSITIVE LOGITS
    that
    0.56
    1
    0.52
    AUT
    0.50
     Opinion
    0.49
    Ｕ
    0.49
    ZU
    0.49
    3
    0.46
    PL
    0.45
     <=
    0.45
     Lic
    0.45
    Activations Density 0.000%

    No Known Activations