© 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. 221605
    Prev
    Next
    INDEX
    Explanations

    Uptown style

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

    markers for concepts

    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
    ﻙ
    0.49
     maximise
    0.48
     dirigeants
    0.48
     frontman
    0.48
     শান্তির
    0.47
    enzi
    0.46
     картина
    0.46
     rehabilitate
    0.46
     realizzare
    0.44
     germinate
    0.44
    POSITIVE LOGITS
     infinitesimal
    0.47
    ऋ
    0.46
     Dose
    0.45
     infrared
    0.44
    attle
    0.43
    Break
    0.43
     Drinfeld
    0.43
    ').
    0.43
     Bode
    0.42
     Corps
    0.42
    Activations Density 0.001%

    No Known Activations