© 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. 35878
    Prev
    Next
    INDEX
    Explanations

    carry all, small goal, Unique leather, day remarkably, under Section, cask beers

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

    diligently tending

    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
    ذك
    0.48
     ryt
    0.44
     샘
    0.43
    ждением
    0.43
    បញ្ចប់
    0.43
    ดัง
    0.42
     papá
    0.42
     comprim
    0.42
     Bakan
    0.42
     latent
    0.42
    POSITIVE LOGITS
    Attractive
    0.53
     ассорти
    0.51
     attuale
    0.51
    ى
    0.49
     endeavoured
    0.47
    isesti
    0.46
    राकी
    0.46
    ialize
    0.46
     dynamite
    0.45
    계
    0.45
    Activations Density 0.000%

    No Known Activations