© 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. 41355
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    designed to question or explain

    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
     decency
    0.45
     dungeon
    0.45
     dungeons
    0.43
     harrowing
    0.43
     kiosks
    0.42
    ’
    0.42
     horrors
    0.41
     mortars
    0.41
    fantastic
    0.41
     macer
    0.40
    POSITIVE LOGITS
     від
    0.52
     프로젝트
    0.49
    竝
    0.49
     проекту
    0.46
     menurut
    0.46
     volgens
    0.45
     синх
    0.45
     โดย
    0.44
     변화
    0.44
     согласно
    0.43
    Activations Density 0.000%

    No Known Activations