© 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. 103914
    Prev
    Next
    INDEX
    Explanations

    develop global, inherited from

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

    circle followed by circular or in

    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
    s
    0.60
    k
    0.57
    es
    0.55
    स्
    0.55
    m
    0.52
    v
    0.52
     Contact
    0.51
    g
    0.51
    sht
    0.50
     State
    0.49
    POSITIVE LOGITS
     irradi
    0.44
    pieceSelection
    0.44
    '><
    0.42
    γι
    0.42
    最优
    0.40
     ribosomal
    0.40
    ርስ
    0.40
     درجہ
    0.40
     বুকের
    0.40
    Parrocchia
    0.39
    Activations Density 0.000%

    No Known Activations