© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    helpful for businesses

    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
    v
    0.57
    tt
    0.52
    nd
    0.51
     -
    0.51
    x
    0.51
    o
    0.47
    ICATION
    0.46
    tic
    0.46
    ttt
    0.46
    rd
    0.46
    POSITIVE LOGITS
    Zawodnik
    0.47
     শ্রমিক
    0.47
    Participants
    0.47
     শ্রম
    0.46
     Gippsland
    0.45
     Participant
    0.44
    “…
    0.43
    রোগ
    0.43
    蔺
    0.43
    搠
    0.43
    Activations Density 0.001%

    No Known Activations