© 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. 97050
    Prev
    Next
    INDEX
    Explanations

    saving money and preserving value

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

    list context

    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
     التر
    0.56
    ed
    0.51
    PTS
    0.50
    RK
    0.50
     impartial
    0.50
     trademarks
    0.49
    K
    0.48
    PAT
    0.48
     unmistakable
    0.48
     ordinances
    0.47
    POSITIVE LOGITS
     Cantor
    0.51
    সুতরাং
    0.47
     मोल
    0.44
     অবসর
    0.44
    yser
    0.43
     अभिषेक
    0.43
    द्योगिक
    0.43
    芴
    0.43
    rifice
    0.43
     সুতরাং
    0.43
    Activations Density 0.000%

    No Known Activations