© 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. 99361
    Prev
    Next
    INDEX
    Explanations

    daily log, directorial debut, interview was

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

    charge to card

    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
    in
    0.55
    ikom
    0.54
    alaikums
    0.50
    o
    0.49
     ആഘോഷ
    0.48
    positroid
    0.48
     esigen
    0.47
     castom
    0.47
    <unused40>
    0.46
     आतंकियों
    0.46
    POSITIVE LOGITS
     and
    0.51
     stabbing
    0.44
     pedig
    0.44
     passing
    0.42
     ethnographic
    0.41
    byn
    0.41
     seating
    0.41
     coal
    0.40
     wading
    0.40
     migratory
    0.39
    Activations Density 0.000%

    No Known Activations