© 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. 49635
    Prev
    Next
    INDEX
    Explanations

    unique form, video files

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

    "Must" followed by "Have" or hyphen

    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
    NAC
    0.45
    𝗙
    0.45
    FUN
    0.44
    আবার
    0.43
    cznym
    0.42
    সঙ্গত
    0.42
     FUN
    0.41
     आओ
    0.40
    🐍
    0.40
    Covid
    0.39
    POSITIVE LOGITS
    usahaan
    0.52
    ⱼ
    0.46
     판매
    0.44
     stockholders
    0.44
     manic
    0.43
     방송
    0.43
     surveyor
    0.42
     machinist
    0.42
     sue
    0.41
     brewer
    0.41
    Activations Density 0.001%

    No Known Activations