© 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. 27350
    Prev
    Next
    INDEX
    Explanations

    date & time indicators

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

    AWS Activate credit

    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
     spotting
    0.48
     enhancing
    0.47
     acids
    0.47
     Tables
    0.44
    摘要
    0.43
     providing
    0.43
     acide
    0.42
    ၍
    0.42
     the
    0.41
     acides
    0.41
    POSITIVE LOGITS
    DUT
    0.48
     («
    0.43
    !!!!!
    0.43
    ❌
    0.42
    🥳
    0.42
    சரி
    0.42
    !!!!!!!!!!!!!!!!
    0.42
    Adress
    0.41
    🤕
    0.41
    ठीक
    0.41
    Activations Density 0.000%

    No Known Activations