© 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. 33212
    Prev
    Next
    INDEX
    Explanations

    vacuum pump 70

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

    Once hatched, process String

    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
    廖
    0.48
    隗
    0.46
    掣
    0.46
    ό
    0.45
    ಾರ್
    0.45
    ब्
    0.42
    中共
    0.42
    ﻔ
    0.42
    ﺎ
    0.41
    有一
    0.41
    POSITIVE LOGITS
    puted
    0.52
     asas
    0.51
     väl
    0.50
    yek
    0.49
     temperat
    0.49
     neid
    0.48
    यला
    0.48
     fürs
    0.47
    me
    0.47
     olisi
    0.47
    Activations Density 0.000%

    No Known Activations