© 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. 155006
    Prev
    Next
    INDEX
    Explanations

    names and descriptions of states

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

    refining processes and formulas

    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
    reports
    0.49
    regulatory
    0.48
    throughput
    0.48
    ceived
    0.46
    humidity
    0.46
    "/
    0.46
    ွက်
    0.45
    crack
    0.45
     sleepers
    0.45
    longitude
    0.44
    POSITIVE LOGITS
     BFF
    0.59
     Sol
    0.51
     Algar
    0.51
     Rodr
    0.50
     Samantha
    0.50
     B
    0.50
     S
    0.49
     Rodriguez
    0.49
     namani
    0.49
     Domino
    0.49
    Activations Density 0.000%

    No Known Activations