© 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. 172489
    Prev
    Next
    INDEX
    Explanations

    additional copies and shared services

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

    mountain, bridge, BI reports

    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
    })$.
    0.50
    haven
    0.47
    videmment
    0.44
    仕方
    0.44
    })+
    0.43
    initi
    0.43
     bevy
    0.43
     sizzling
    0.43
    fif
    0.42
    fifth
    0.42
    POSITIVE LOGITS
    кну
    0.46
     प्रशिक्षित
    0.46
     Оксана
    0.46
    িস্টার
    0.45
    ステン
    0.45
    ிய
    0.44
    コス
    0.44
    ﻡ
    0.44
    лу
    0.43
     Increase
    0.43
    Activations Density 0.000%

    No Known Activations