© 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. 40-GEMMASCOPE-2-RES-16K
    7. 12028
    Prev
    Next
    INDEX
    Explanations

    another, predictable negative reaction

    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_40_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
     훨씬
    0.45
    ங்கோ
    0.44
     hex
    0.40
    раздо
    0.40
    াটো
    0.39
    ！）
    0.39
     kich
    0.38
    ;)
    0.38
    uid
    0.38
     உரிமை
    0.38
    POSITIVE LOGITS
    🤦
    0.82
    🙄
    0.67
    😑
    0.62
     wonderful
    0.54
    😒
    0.53
     predictable
    0.52
    wonderful
    0.52
     predictably
    0.50
    🤮
    0.49
     obligatory
    0.49
    Activations Density 0.099%

    No Known Activations