© 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-65K
    7. 8945
    Prev
    Next
    INDEX
    Explanations

    user queries

    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
     (+
    0.57
     (&
    0.52
     (“
    0.47
     (
    0.47
     ("
    0.47
     inescap
    0.47
     deftly
    0.46
     Supplemental
    0.44
     hedon
    0.44
     tempore
    0.44
    POSITIVE LOGITS
    sorry
    0.62
     sorry
    0.58
     اكبر
    0.55
     बच्चो
    0.54
    finaly
    0.53
    varage
    0.53
     plz
    0.52
    comend
    0.50
    indx
    0.49
    맟
    0.49
    Activations Density 0.216%

    No Known Activations