© 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. 47820
    Prev
    Next
    INDEX
    Explanations

    can help greatly

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

    directory named

    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
    xx
    0.44
    ᆻ
    0.44
    cmp
    0.43
    col
    0.41
    描
    0.41
    xy
    0.40
     scene
    0.40
    xml
    0.39
    雲
    0.39
    scene
    0.38
    POSITIVE LOGITS
     jednego
    0.51
     hänen
    0.48
     तरा
    0.47
     hypertrophy
    0.46
     inclui
    0.46
     afili
    0.46
    莴
    0.46
     énorme
    0.45
     kanyang
    0.45
     ainult
    0.45
    Activations Density 0.000%

    No Known Activations