© 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. 54054
    Prev
    Next
    INDEX
    Explanations

    describes states or outcomes

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

    strong abilities and performance

    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
    бед
    0.46
    ურთი
    0.45
    शेदपुर
    0.44
    Benjamin
    0.44
     какое
    0.43
    櫻
    0.43
    鳕
    0.43
    abilität
    0.42
    শেখ
    0.42
    Suzanne
    0.42
    POSITIVE LOGITS
     combines
    0.55
     Latest
    0.50
     gathers
    0.50
     Provides
    0.49
     Raises
    0.48
     celebrates
    0.45
     adore
    0.45
     DI
    0.45
     Allows
    0.45
    }\
    0.44
    Activations Density 0.000%

    No Known Activations