© 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. 40-GEMMASCOPE-2-RES-262K
    7. 33529
    Prev
    Next
    INDEX
    Explanations

    language 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_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
     evolving
    0.42
    ▌
    0.40
    #!/
    0.40
    /**/*.{
    0.38
     motorised
    0.37
     varying
    0.37
    κης
    0.37
    >≥</
    0.37
    μεσα
    0.37
     endeavoured
    0.36
    POSITIVE LOGITS
     noun
    0.46
     لفظ
    0.45
     Wörter
    0.41
     वाक्यांश
    0.41
     शब्द
    0.39
    italic
    0.39
     nouns
    0.39
    gloss
    0.39
     adverb
    0.38
     pronoun
    0.38
    Activations Density 0.023%

    No Known Activations