© 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. 242307
    Prev
    Next
    INDEX
    Explanations

    foreign places and things

    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
     +
    0.54
     sized
    0.53
     cosi
    0.52
     was
    0.51
     align
    0.51
     prefix
    0.51
     specific
    0.50
     REST
    0.50
     einfacher
    0.50
     GraphQL
    0.50
    POSITIVE LOGITS
    terrorism
    0.63
     आतंकवाद
    0.55
    -
    0.55
    Connecticut
    0.52
    iteracy
    0.52
     dünyaya
    0.52
    ırm
    0.51
    terror
    0.51
    politics
    0.51
     జరుగు
    0.50
    Activations Density 0.000%

    No Known Activations