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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42157
    Prev
    Next
    INDEX
    Explanations

    learning paths

    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
    .
    0.45
    ansa
    0.44
    à
    0.44
    ço
    0.44
    <0xF3>
    0.43
    ⛈
    0.43
    <0xDF>
    0.42
    इ
    0.42
     сохранения
    0.42
    ée
    0.41
    POSITIVE LOGITS
     легче
    0.42
     পুস্তকের
    0.42
    ংকের
    0.41
     ترقی
    0.40
    صبحت
    0.40
    филлер
    0.39
     furtherance
    0.39
     కృషి
    0.39
     aforementioned
    0.39
     internalized
    0.39
    Activations Density 0.014%

    No Known Activations