© 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. 31-GEMMASCOPE-2-RES-262K
    7. 47421
    Prev
    Next
    INDEX
    Explanations

    assertions of known facts

    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_31_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
    农民
    0.40
    讳
    0.40
    𝒖
    0.39
    shi
    0.38
     හැ
    0.36
    tait
    0.36
    lių
    0.36
    まり
    0.36
    节点的
    0.35
    涀
    0.35
    POSITIVE LOGITS
     clamping
    0.53
     catches
    0.52
     wiggle
    0.50
     landed
    0.47
     loosening
    0.47
     tripped
    0.46
     there
    0.46
     chance
    0.46
    gripper
    0.46
     clings
    0.45
    Activations Density 0.001%

    No Known Activations