© 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. 225090
    Prev
    Next
    INDEX
    Explanations

    time periods and their ends

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

    choices or alternatives

    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
    rière
    0.44
    toHave
    0.44
    ër
    0.43
     ภาพ
    0.43
    ᇁ
    0.42
     Film
    0.41
     aspectRatio
    0.41
     borderRadius
    0.40
    áneamente
    0.40
     Formation
    0.39
    POSITIVE LOGITS
    )+\
    0.48
    +)
    0.45
    ប្រើ
    0.45
     そんな
    0.43
     uitge
    0.43
    equival
    0.43
     neki
    0.42
    そんな
    0.42
     sekal
    0.42
     थोड़े
    0.42
    Activations Density 0.002%

    No Known Activations