© 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. 71928
    Prev
    Next
    INDEX
    Explanations

    editing sections or details

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

    edit button

    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
    standen
    0.48
    <0x95>
    0.47
     XXIII
    0.46
    runde
    0.46
    rentices
    0.45
    arati
    0.44
    slit
    0.44
    sec
    0.44
     Thirteen
    0.43
    pleri
    0.43
    POSITIVE LOGITS
    難しい
    0.48
     aval
    0.46
     dun
    0.46
    出
    0.46
     ideally
    0.45
    กก
    0.45
     mapa
    0.43
     ud
    0.43
     pari
    0.43
     dado
    0.43
    Activations Density 0.000%

    No Known Activations