© 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. 224200
    Prev
    Next
    INDEX
    Explanations

    signing frame

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

    Discord accounts and servers

    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
     kumb
    0.47
     る
    0.45
    ар
    0.45
     완전히
    0.45
     kanilang
    0.44
    िन
    0.43
     arbres
    0.43
     puluh
    0.43
    і
    0.43
    ங்க
    0.42
    POSITIVE LOGITS
    s
    0.57
    評論
    0.56
    lblCredits
    0.49
     Stories
    0.49
    kken
    0.48
     leveraged
    0.48
    にあった
    0.48
    ၷ
    0.47
    eve
    0.46
    sframe
    0.46
    Activations Density 0.001%

    No Known Activations