© 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. 106975
    Prev
    Next
    INDEX
    Explanations

    after ... followed by

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

    listing steps or actions

    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
     venturing
    0.46
    權
    0.46
     escrow
    0.44
     devoid
    0.44
     abolition
    0.44
    也不
    0.43
     without
    0.42
     garantías
    0.42
     inception
    0.41
     Chung
    0.41
    POSITIVE LOGITS
    িয়াছে
    0.51
     학교
    0.45
    学校
    0.45
    학교
    0.45
     शाळा
    0.44
    骤
    0.43
    Knowledge
    0.42
     처리
    0.42
    滘
    0.41
    irthday
    0.40
    Activations Density 0.000%

    No Known Activations