© 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. 3033
    Prev
    Next
    INDEX
    Explanations

    purpose or reason

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

    for free/custom/a

    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
    I
    0.43
    ম
    0.42
     ਹੈ
    0.40
    O
    0.40
    ißler
    0.39
    F
    0.39
    D
    0.39
    শ
    0.39
    in
    0.38
    어
    0.38
    POSITIVE LOGITS
     purposes
    0.46
     sake
    0.43
    ked
    0.39
    asmuch
    0.39
    giveness
    0.37
    geries
    0.34
     this
    0.33
    erun
    0.33
     constant
    0.32
    чан
    0.32
    Activations Density 0.425%

    No Known Activations