© 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. 151889
    Prev
    Next
    INDEX
    Explanations

    common terms

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

    specializes, design, might, quick

    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
    ધ
    0.48
    խ
    0.48
     quiso
    0.47
    <strong>
    0.47
     când
    0.47
     finne
    0.46
    𝐂
    0.46
    hindi
    0.45
    することで
    0.45
    (+
    0.45
    POSITIVE LOGITS
    リーズ
    0.44
     تو
    0.42
    linie
    0.42
    벧
    0.41
     engages
    0.40
     maximally
    0.40
     specialise
    0.39
     radiates
    0.39
    ლის
    0.39
     denote
    0.39
    Activations Density 0.000%

    No Known Activations