© 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. 180937
    Prev
    Next
    INDEX
    Explanations

    windy hill

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

    frequent relative to

    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
    ారి
    0.49
    ೩
    0.47
    踺
    0.46
     SULF
    0.46
    ಣೆ
    0.45
    éph
    0.45
    ebut
    0.44
     Synthetic
    0.44
     네트워크
    0.44
    𒀀
    0.44
    POSITIVE LOGITS
    Tree
    0.46
    CodeGen
    0.44
     totem
    0.42
    BST
    0.42
     constituent
    0.41
    InCM
    0.41
     consac
    0.40
    居
    0.40
    เป็น
    0.40
     constituer
    0.40
    Activations Density 0.001%

    No Known Activations