© 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. 40-GEMMASCOPE-2-RES-262K
    7. 17597
    Prev
    Next
    INDEX
    Explanations

    reports speech or explanation

    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_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
    vergne
    0.40
    Would
    0.39
    girlfriend
    0.39
    Reality
    0.37
    lastIndexOf
    0.37
    Honestly
    0.37
    するなど
    0.37
    ()){
    0.36
    Assume
    0.36
    avacanam
    0.35
    POSITIVE LOGITS
    他说
    0.74
    他說
    0.73
    她说
    0.64
     says
    0.63
     বলেন
    0.60
     என்கிறார்
    0.59
     explains
    0.59
     explicó
    0.58
     pihaknya
    0.58
    ందన్నారు
    0.58
    Activations Density 0.001%

    No Known Activations