© 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-262K
    7. 38120
    Prev
    Next
    INDEX
    Explanations

    introducing descriptive phrases

    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
    纍
    0.48
    ंकन
    0.47
     pemberian
    0.45
    varlak
    0.45
     Поль
    0.43
     חלק
    0.43
    蹩
    0.43
    érance
    0.43
    FreeFlag
    0.43
     बैठक
    0.43
    POSITIVE LOGITS
    u
    0.52
    一种
    0.47
    is
    0.45
    （
    0.44
     isa
    0.44
    in
    0.43
    入
    0.42
    育
    0.42
     OMX
    0.41
     This
    0.40
    Activations Density 0.004%

    No Known Activations