© 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. 116377
    Prev
    Next
    INDEX
    Explanations

    listing items and consequences

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

    tracking, appointment, challenge

    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
    اء
    0.51
    ிய
    0.48
    ات
    0.45
    او
    0.44
    ナー
    0.44
    𝘢
    0.43
    га
    0.43
    ས་
    0.43
    ﻠ
    0.43
     отсутствии
    0.42
    POSITIVE LOGITS
    venes
    0.49
     LARGE
    0.48
     shaver
    0.48
     stort
    0.46
     pagoda
    0.45
    anyahu
    0.45
    "./
    0.44
     speaker
    0.44
    Csvg
    0.44
     zeggen
    0.44
    Activations Density 0.001%

    No Known Activations