© 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. 8985
    Prev
    Next
    INDEX
    Explanations

    foreign words and reset/method

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

    improvements and explanations

    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
    github
    0.30
    q
    0.24
    King
    0.24
    Getty
    0.24
     září
    0.24
    Bit
    0.24
    Evans
    0.24
    Disk
    0.23
    Bloomberg
    0.23
    Symfony
    0.23
    POSITIVE LOGITS
    этому
    0.28
     trase
    0.26
     แล้ว
    0.26
     entren
    0.26
     специ
    0.25
     conserva
    0.25
    럼
    0.25
     สม
    0.25
     Guatem
    0.25
     stupe
    0.24
    Activations Density 0.498%

    No Known Activations