© 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. 83008
    Prev
    Next
    INDEX
    Explanations

    identifying emotions and classifications

    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
    de
    0.52
    あ
    0.48
     croc
    0.44
    いた
    0.43
     Prussia
    0.43
    и
    0.42
    ρα
    0.42
     வேண்டும்
    0.42
     regrett
    0.42
    ーズ
    0.42
    POSITIVE LOGITS
     numerosos
    0.50
    <unused58>
    0.43
    🚒
    0.43
     ہوسک
    0.41
    atthaya
    0.40
     ভবিষ্যতে
    0.40
    IGroup
    0.40
     volo
    0.40
     برخی
    0.39
     چنان
    0.39
    Activations Density 0.001%

    No Known Activations