© 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. 201888
    Prev
    Next
    INDEX
    Explanations

    click Download

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

    choices and statements

    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
     周
    0.47
    周
    0.46
    λώ
    0.44
     옳
    0.44
    COPY
    0.43
    STORE
    0.43
     সমী
    0.43
    ACM
    0.43
     рису
    0.42
    STOCK
    0.42
    POSITIVE LOGITS
    collide
    0.48
     Vorteil
    0.46
    ":[{"
    0.45
    ้ํา
    0.45
     standpoint
    0.41
     berjudul
    0.41
    ാല്‍
    0.41
     bedeut
    0.40
     Spacious
    0.40
     svjet
    0.40
    Activations Density 0.000%

    No Known Activations