© 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. 28026
    Prev
    Next
    INDEX
    Explanations

    apoptosome, dice, cataract, clinker, grinding, podocytes, wanding

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

    qubit, machine, auxin, epsilon

    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
    נו
    0.50
    ยาน
    0.49
    ERIAL
    0.47
    呠
    0.46
    เม
    0.45
     но
    0.44
     displayName
    0.44
    ७
    0.44
    רו
    0.43
    เร
    0.42
    POSITIVE LOGITS
    による
    0.55
     selaku
    0.50
     cuja
    0.49
    говори
    0.46
     द्वारा
    0.46
     cuya
    0.45
    と呼ばれる
    0.44
     efficacement
    0.44
     wodurch
    0.44
     দ্বারা
    0.43
    Activations Density 0.006%

    No Known Activations