© 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-16K
    7. 3329
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ىن
    0.52
    <0x80>
    0.51
    io
    0.51
    us
    0.50
    ônio
    0.48
    ější
    0.47
     técnicos
    0.47
    ai
    0.47
    esar
    0.46
     médicos
    0.45
    POSITIVE LOGITS
    0.59
     chảy
    0.49
    ”،
    0.49
    樺
    0.48
    }>
    0.47
    ה
    0.46
    luğu
    0.46
    ุ
    0.46
    }-
    0.46
    AK
    0.46
    Activations Density 0.161%

    No Known Activations