© 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. 191586
    Prev
    Next
    INDEX
    Explanations

    affiliate links, salt lake, beads held

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

    Redis deployment and service

    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
    AT
    0.51
    Fus
    0.48
    ції
    0.47
    握
    0.46
    MeV
    0.45
    men
    0.45
     Intell
    0.45
    FE
    0.43
     обе
    0.43
    *;
    0.43
    POSITIVE LOGITS
     assh
    0.50
     instytuc
    0.48
     splashes
    0.48
    čak
    0.47
     parasites
    0.46
     photographs
    0.46
     saurait
    0.45
     daydream
    0.45
     authenticity
    0.44
     pirates
    0.44
    Activations Density 0.000%

    No Known Activations