© 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. 60432
    Prev
    Next
    INDEX
    Explanations

    finding parts or inventory

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

    ordered in, supply chain

    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
     Cler
    0.46
    ous
    0.44
    Olivier
    0.44
    cler
    0.42
     sozialen
    0.41
     Jorn
    0.40
    Vere
    0.40
    Ᏼ
    0.39
     노동
    0.39
    conti
    0.39
    POSITIVE LOGITS
    伝説
    0.49
     nunca
    0.44
    突破
    0.44
     обнаружи
    0.42
     possibilidade
    0.42
     RESERVE
    0.41
    機種
    0.40
     Nunca
    0.39
     unanticipated
    0.39
    supabase
    0.39
    Activations Density 0.001%

    No Known Activations