© 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. 218936
    Prev
    Next
    INDEX
    Explanations

    share or send

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

    fish, water, trade, locations

    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
     Unilever
    0.46
     Dynkin
    0.44
     nouveau
    0.43
     $\
    0.42
    bon
    0.42
     zehn
    0.42
    brä
    0.41
     glaube
    0.41
     Theorie
    0.41
     nouvelle
    0.41
    POSITIVE LOGITS
    Nationality
    0.55
     तस्वीरों
    0.47
    কাত
    0.45
    Assassin
    0.45
     обслуживания
    0.44
    িয়াল
    0.44
    ”
    0.44
    Sunset
    0.43
    ের
    0.42
     किरदार
    0.42
    Activations Density 0.000%

    No Known Activations