© 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. 188789
    Prev
    Next
    INDEX
    Explanations

    asbestos and transition

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

    prioritize proper form

    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
    0
    0.53
     tuple
    0.52
     tuples
    0.52
    us
    0.50
     third
    0.48
    t
    0.48
    third
    0.46
    tuple
    0.45
     topologically
    0.45
     thirds
    0.45
    POSITIVE LOGITS
     ότι
    0.54
    祂
    0.52
     pourra
    0.50
     θέ
    0.50
     त्याचे
    0.50
     etapas
    0.49
     भागात
    0.49
     Без
    0.48
     डील
    0.48
     आपले
    0.48
    Activations Density 0.000%

    No Known Activations