© 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. 131893
    Prev
    Next
    INDEX
    Explanations

    many collections

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

    lightning bolt

    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
    綱
    0.55
    ת
    0.52
    अधिकांश
    0.50
    国
    0.50
    ל
    0.50
    性
    0.50
    Actual
    0.49
    實際
    0.48
    実際に
    0.48
    楽
    0.48
    POSITIVE LOGITS
     entryway
    0.45
     عفوا
    0.45
    avano
    0.45
     unfinished
    0.44
     మహిళ
    0.43
    annonce
    0.43
     undone
    0.43
    kker
    0.43
    emplates
    0.43
    elom
    0.43
    Activations Density 0.000%

    No Known Activations