© 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. 151021
    Prev
    Next
    INDEX
    Explanations

    inquiry descriptions host changed

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

    legal significance, Communist Theory, celestial heritage

    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
    ამართ
    0.48
    ленные
    0.46
     hyperlocal
    0.45
    痢
    0.44
    하면
    0.44
     trivalent
    0.43
     통한
    0.43
     phạt
    0.42
     वेतन
    0.42
     반갑습니다
    0.42
    POSITIVE LOGITS
    \
    0.52
     astronomy
    0.43
    ۲
    0.42
    probabilities
    0.40
     probabilities
    0.40
     Ts
    0.39
     bekannten
    0.39
     Ta
    0.38
    Н
    0.38
     Chances
    0.38
    Activations Density 0.003%

    No Known Activations