© 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. 49065
    Prev
    Next
    INDEX
    Explanations

    legal, books, or proper names

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

    state management

    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
    ﻥ
    0.52
    命运
    0.50
    锷
    0.46
    пущен
    0.44
    حن
    0.44
     misión
    0.42
     meghatá
    0.41
    蔵
    0.41
    вање
    0.41
     Posteriormente
    0.41
    POSITIVE LOGITS
     Everyday
    0.50
     आयकर
    0.50
     everyday
    0.49
    obi
    0.47
    greater
    0.46
    matically
    0.45
    Function
    0.45
    na
    0.44
    രിയാ
    0.44
     beaches
    0.44
    Activations Density 0.000%

    No Known Activations