© 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. 201014
    Prev
    Next
    INDEX
    Explanations

    .com web

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

    costly outcomes and avoiding them

    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
    ET
    0.55
    pio
    0.51
    rrh
    0.51
    pink
    0.50
    I
    0.50
    ir
    0.49
    ਪ
    0.48
    nda
    0.48
    blic
    0.48
    ่
    0.47
    POSITIVE LOGITS
     Matching
    0.50
    ஷன்
    0.49
     Driver
    0.46
     TTL
    0.46
     Ủy
    0.46
     Debug
    0.45
     Fighter
    0.44
     Hành
    0.44
     ống
    0.43
     wheelbase
    0.43
    Activations Density 0.000%

    No Known Activations