© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56212
    Prev
    Next
    INDEX
    Explanations

    negative judgment on descriptions

    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_65k_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
     மற்றும்
    0.54
    /
    0.53
     మరియు
    0.47
    Ин
    0.46
     EXPER
    0.46
     ಮತ್ತು
    0.44
     சிகிச்ச
    0.44
    т
    0.43
    ி
    0.43
    ت
    0.42
    POSITIVE LOGITS
     immoral
    0.51
     blackmail
    0.49
     الدنيا
    0.49
     multinationals
    0.48
     meagre
    0.48
     ridicule
    0.47
     disprove
    0.47
     malign
    0.47
     scanty
    0.46
     petty
    0.46
    Activations Density 0.010%

    No Known Activations