© 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. 17537
    Prev
    Next
    INDEX
    Explanations

    classification types and specific domains

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

    types, keys, and subclasses

    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
    that
    0.54
    она
    0.53
    не
    0.50
    plus
    0.49
    те
    0.48
    ті
    0.48
    イ
    0.48
    want
    0.47
    which
    0.46
    1
    0.46
    POSITIVE LOGITS
     analogues
    0.47
     类型
    0.47
     dosages
    0.47
     electroph
    0.45
     entsprechenden
    0.44
     relevant
    0.43
     サマータイヤ
    0.42
     SLAs
    0.42
     例如
    0.42
     Types
    0.41
    Activations Density 0.001%

    No Known Activations