© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 136884
    Prev
    Next
    INDEX
    Explanations

    physical states and parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getLocation
    0.47
    ֆ
    0.42
     зимой
    0.42
    плуа
    0.41
     الثاني
    0.41
     dijal
    0.41
    髡
    0.41
    教學
    0.40
    त्र
    0.39
    teaching
    0.39
    POSITIVE LOGITS
     unstable
    0.46
     green
    0.45
     lemon
    0.44
     one
    0.43
     pre
    0.43
     shock
    0.43
     rare
    0.43
     unsteady
    0.43
     them
    0.42
     gre
    0.42
    Activations Density 0.006%

    No Known Activations