© 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. 144891
    Prev
    Next
    INDEX
    Explanations

    download files and images

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

    action followed by next step

    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
    ਹੀ
    0.50
     kõ
    0.49
     LaserJet
    0.49
     Test
    0.49
    펄
    0.46
     pomoć
    0.46
     kepada
    0.46
     déplacement
    0.46
    ั
    0.45
    疳
    0.45
    POSITIVE LOGITS
    is
    0.53
    irán
    0.52
    ashov
    0.48
     Denton
    0.47
     Concepción
    0.47
    faf
    0.46
    standing
    0.46
    wu
    0.46
     deterred
    0.46
    can
    0.46
    Activations Density 0.001%

    No Known Activations