© 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. 196539
    Prev
    Next
    INDEX
    Explanations

    Texas Longhorns, coupled simulation, in health

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

    print and Russian

    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
    committee
    0.53
    時間
    0.48
    threat
    0.48
    ാന
    0.48
     zasad
    0.48
    pok
    0.47
    nière
    0.47
     ഭ
    0.46
    シー
    0.45
    et
    0.45
    POSITIVE LOGITS
     Economies
    0.44
     Enrichment
    0.43
     wreck
    0.43
     accel
    0.42
     Biology
    0.40
     Taxonomy
    0.40
    вано
    0.40
    ఊ
    0.40
     primeiros
    0.39
     enrichment
    0.39
    Activations Density 0.001%

    No Known Activations