© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8434
    Prev
    Next
    INDEX
    Explanations

    A with numbers

    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
    }*/
    0.47
    uetooth
    0.46
    こちら
    0.45
    TabView
    0.44
    idges
    0.43
    UCLEAR
    0.42
    vdd
    0.42
    。</
    0.42
    要注意
    0.42
    esgue
    0.41
    POSITIVE LOGITS
    忆
    0.43
    勮
    0.42
    Herb
    0.41
     Herbal
    0.41
     instinct
    0.41
    蠶
    0.41
     Prabh
    0.40
     Kubo
    0.40
    澼
    0.40
     POV
    0.40
    Activations Density 0.001%

    No Known Activations