© 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. 32942
    Prev
    Next
    INDEX
    Explanations

    archived information from sources

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

    encyclopedic web content

    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
    MakeRect
    0.46
     pretends
    0.45
     lehető
    0.44
    ರುವುದರಿಂದ
    0.44
    రిగి
    0.44
     eignet
    0.44
    痔
    0.42
    allows
    0.42
    毉
    0.42
    ालत
    0.42
    POSITIVE LOGITS
     Archived
    0.67
     History
    0.61
     List
    0.56
     Profile
    0.54
     Archive
    0.52
     Archives
    0.52
     Encyclopædia
    0.52
     Encyclopedia
    0.52
     http
    0.51
     Database
    0.51
    Activations Density 0.028%

    No Known Activations