© 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. 116092
    Prev
    Next
    INDEX
    Explanations

    specialized terms and non-English words

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

    many Transformer variants

    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
    ning
    0.44
    ic
    0.44
    ン
    0.44
    น
    0.42
    sty
    0.41
    Parameter
    0.41
    payment
    0.41
     व
    0.41
     pe
    0.41
    ন
    0.41
    POSITIVE LOGITS
     حدیث
    0.46
     ilgi
    0.46
     çeşit
    0.45
     campaigner
    0.45
     شرطونو
    0.45
     Gifford
    0.44
     azar
    0.43
     compartido
    0.43
    íž
    0.43
     agir
    0.43
    Activations Density 0.001%

    No Known Activations