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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7767
    Prev
    Next
    INDEX
    Explanations

    materials and categories

    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
    ufthansa
    0.47
     לק
    0.46
    asshi
    0.46
    셸
    0.46
     использоваться
    0.45
     здраво
    0.44
     використовувати
    0.44
    urst
    0.44
     рішення
    0.44
    雳
    0.44
    POSITIVE LOGITS
    s
    0.59
     emotions
    0.47
     telah
    0.47
    Materials
    0.47
     materials
    0.46
     filters
    0.46
     chemicals
    0.45
     toys
    0.45
     artefacts
    0.45
     responders
    0.45
    Activations Density 0.010%

    No Known Activations