© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4136
    Prev
    Next
    INDEX
    Explanations

    phrases starting with just

    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_16k_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
     enjoy
    0.33
    T
    0.32
    H
    0.30
    D
    0.30
     haver
    0.29
    cia
    0.29
    -
    0.29
    W
    0.29
    Y
    0.29
     remain
    0.29
    POSITIVE LOGITS
    一个小
    0.29
    PostMapping
    0.27
    り
    0.26
    اتها
    0.26
    ول
    0.25
    лишком
    0.25
     작은
    0.25
    ﷼
    0.25
    лина
    0.25
    ঙ্কা
    0.25
    Activations Density 0.168%

    No Known Activations