© 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. 48475
    Prev
    Next
    INDEX
    Explanations

    CENTERVILLE and related place names

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

    cities and states

    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
    潭
    0.36
    󠁳
    0.34
    ؛
    0.34
     منسل
    0.34
     নগর
    0.33
    يل
    0.33
     подклю
    0.33
    шчы
    0.33
    ட்ரா
    0.33
     বন
    0.33
    POSITIVE LOGITS
     initial
    0.34
     potential
    0.33
     imputed
    0.33
     Im
    0.32
     r
    0.32
     Initial
    0.31
    ase
    0.31
     Fab
    0.31
     potent
    0.31
     ISI
    0.31
    Activations Density 0.017%

    No Known Activations