© 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. 212345
    Prev
    Next
    INDEX
    Explanations

    body parts and structure

    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
     ইন্দুর
    0.54
     판매
    0.49
     삽니다
    0.47
     ಬಾರಿ
    0.46
     mineralization
    0.45
     terpenes
    0.45
     खुराक
    0.45
    ƌ
    0.45
     dimensionality
    0.44
     상승
    0.44
    POSITIVE LOGITS
    所谓
    0.44
    囹
    0.44
    所谓的
    0.42
    在这种
    0.41
    倘
    0.41
    这个
    0.40
    简介
    0.39
    California
    0.39
     "*************"
    0.39
     Visiting
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.