© 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. 223143
    Prev
    Next
    INDEX
    Explanations

    backup strategies, hardware, and food items

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

    a fortified

    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
    рита
    0.53
     खेतों
    0.51
    คะ
    0.50
    huis
    0.50
    t
    0.50
    う
    0.48
    ר
    0.46
    Luis
    0.46
    blems
    0.46
    Bingo
    0.45
    POSITIVE LOGITS
     peritone
    0.44
     بیم
    0.42
     电
    0.42
     Vign
    0.42
     ergonomic
    0.41
     collapse
    0.41
     Collapse
    0.40
     peritoneal
    0.40
     precedents
    0.40
     vgl
    0.40
    Activations Density 0.001%

    No Known Activations