© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 4385
    Prev
    Next
    INDEX
    Explanations

    foreign languages and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <
    0.51
     la
    0.50
     y
    0.50
     fuente
    0.50
     
    0.49
     n
    0.48
    in
    0.47
    /
    0.46
     source
    0.46
    R
    0.46
    POSITIVE LOGITS
    𒀕
    0.51
     Religions
    0.50
    ュ
    0.50
    રાજ
    0.47
     IUnary
    0.47
     两
    0.47
     आफ्नो
    0.46
    昍
    0.46
     radiographs
    0.46
    еди
    0.46
    Activations Density 0.002%

    No Known Activations