© 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. 57759
    Prev
    Next
    INDEX
    Explanations

    Mr. followed by

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

    funding, victims, policies, drive

    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
    เภ
    0.46
    द्भ
    0.45
     hotline
    0.44
     fea
    0.41
    옴
    0.40
     subsystem
    0.40
    ह
    0.39
    ச்ச
    0.38
    localObject
    0.38
    راء
    0.38
    POSITIVE LOGITS
    niku
    0.52
     людьми
    0.48
    -$
    0.45
     unreasonably
    0.45
     exager
    0.45
     женой
    0.44
     থাকলে
    0.43
     लिमिट
    0.43
    ürü
    0.43
    ure
    0.42
    Activations Density 0.000%

    No Known Activations