© 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. 228166
    Prev
    Next
    INDEX
    Explanations

    resolving legal claims or disputes

    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
    (-
    0.47
    ックス
    0.47
    的孩子
    0.47
     (-
    0.45
     paysans
    0.44
     uniaxial
    0.44
     arbres
    0.43
     ERR
    0.43
     পেল
    0.42
    oviruses
    0.42
    POSITIVE LOGITS
    Spot
    0.47
    cru
    0.45
     పలు
    0.45
    邝
    0.43
    Gold
    0.43
     privy
    0.43
    льд
    0.42
    వారి
    0.41
    contre
    0.41
    ਲਾ
    0.40
    Activations Density 0.001%

    No Known Activations