© 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. 153950
    Prev
    Next
    INDEX
    Explanations

    but then

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

    taking from or giving to

    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
    第七
    0.52
    第五
    0.50
    чется
    0.50
    逖
    0.49
     રસ
    0.47
     convinced
    0.46
     finestra
    0.46
    ંદ
    0.46
    使える
    0.46
    icción
    0.46
    POSITIVE LOGITS
    batas
    0.48
    beds
    0.47
     bushing
    0.46
    K
    0.44
    debug
    0.44
     vyš
    0.44
     acquies
    0.44
    hazardous
    0.44
    GN
    0.43
    stag
    0.43
    Activations Density 0.001%

    No Known Activations