© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    is followed by a connector

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

    is linking words

    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
    '
    0.27
    ’
    0.24
     zweiten
    0.21
     oder
    0.20
    -,
    0.20
    ",
    0.20
    !
    0.20
     برگزار
    0.19
    acles
    0.19
     centrales
    0.19
    POSITIVE LOGITS
     twofold
    0.32
     not
    0.25
     настолько
    0.25
     threefold
    0.24
     dictated
    0.23
     a
    0.23
     certainly
    0.22
    というと
    0.22
     NOT
    0.21
     reminiscent
    0.21
    Activations Density 0.847%

    No Known Activations