© 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. 9931
    Prev
    Next
    INDEX
    Explanations

    negations or evaluations

    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
    其他
    0.61
    ти
    0.56
    お手
    0.53
    या
    0.51
    กับ
    0.50
    表情
    0.50
    Karte
    0.49
    ?
    0.49
    الب
    0.49
    Agregar
    0.48
    POSITIVE LOGITS
     not
    0.71
     blevet
    0.64
     NOT
    0.61
     likely
    0.61
     probably
    0.59
     unacceptable
    0.58
     a
    0.57
     pointless
    0.57
     useless
    0.57
     easier
    0.56
    Activations Density 0.102%

    No Known Activations