© 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. 93864
    Prev
    Next
    INDEX
    Explanations

    input and output

    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
    口
    0.42
     indis
    0.42
     dissoci
    0.41
     manus
    0.39
    真实
    0.39
     නො
    0.39
    acaktır
    0.39
     BOS
    0.39
    alé
    0.39
     अन्यथा
    0.38
    POSITIVE LOGITS
    vient
    0.43
    '،
    0.43
    Kai
    0.42
    潵
    0.42
    igslist
    0.42
    plicator
    0.40
    arrison
    0.39
    allic
    0.39
    راحة
    0.39
    нная
    0.39
    Activations Density 0.001%

    No Known Activations