© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32645
    Prev
    Next
    INDEX
    Explanations

    get under, secure yourself, take shelter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     delicately
    0.46
     malonyl
    0.42
     coder
    0.40
     nhu
    0.40
     subtly
    0.39
    眈
    0.38
    mathscr
    0.38
     douleur
    0.38
     নির্যাতনের
    0.38
     જેના
    0.37
    POSITIVE LOGITS
     sheltering
    1.05
     shelter
    1.02
    躲
    1.02
     hiding
    0.99
     shelters
    0.95
     sheltered
    0.93
     hunk
    0.89
     Shelter
    0.86
     bunkers
    0.85
     bunker
    0.81
    Activations Density 0.002%

    No Known Activations