© 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. 162243
    Prev
    Next
    INDEX
    Explanations

    self and allowing

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

    defining specific nouns

    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
    BRUARY
    0.53
     PRESSURE
    0.51
    Ζ
    0.51
    싹
    0.51
    הר
    0.49
    𝐵
    0.49
    Buttons
    0.48
    H
    0.48
    sectional
    0.47
    ROLLER
    0.47
    POSITIVE LOGITS
     defini
    0.52
    nya
    0.45
     grot
    0.45
     På
    0.44
    перыі
    0.43
    ermanfaat
    0.43
     dham
    0.42
    oters
    0.42
     Sinne
    0.42
     Dunham
    0.42
    Activations Density 0.016%

    No Known Activations