© 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. 112291
    Prev
    Next
    INDEX
    Explanations

    provides insight

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

    operational efficiency

    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
     очки
    0.44
     человек
    0.42
     சிறிது
    0.42
    <0x0E>
    0.41
    Within
    0.41
     cassettes
    0.41
    <0x04>
    0.41
    צ
    0.41
     encomenda
    0.41
    𝓮
    0.40
    POSITIVE LOGITS
     Arrow
    0.45
    বৈশাখ
    0.45
     Schluss
    0.43
     Allgeme
    0.43
    此之外
    0.42
    に至
    0.42
     zuletzt
    0.42
    hnung
    0.41
    খালী
    0.41
    失败
    0.41
    Activations Density 0.001%

    No Known Activations