© 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. 157791
    Prev
    Next
    INDEX
    Explanations

    city names

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

    delta, integers, stock prices

    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
    機種
    0.48
    ధు
    0.46
    íveis
    0.45
    मां
    0.44
     種
    0.42
    jno
    0.42
    linhas
    0.41
    ➀
    0.41
    espèces
    0.41
     方法
    0.40
    POSITIVE LOGITS
     आँख
    0.47
    се
    0.45
     douche
    0.44
     se
    0.44
    strual
    0.43
    क्टर
    0.42
     gering
    0.42
    ە
    0.41
     Reflex
    0.41
    eonium
    0.41
    Activations Density 0.000%

    No Known Activations