© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201292
    Prev
    Next
    INDEX
    Explanations

    cooling, ending in "are", "in", "a"

    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
    юсь
    0.54
    ב
    0.50
    좀
    0.48
    ମ
    0.46
    ה
    0.46
    코드
    0.44
     اوكي
    0.44
    이트
    0.44
    тона
    0.44
    𝙲
    0.44
    POSITIVE LOGITS
    rav
    0.41
    શ્ર
    0.41
     mese
    0.41
    ül
    0.40
    lowing
    0.39
     centuries
    0.39
     dowol
    0.39
    ukh
    0.38
     conservation
    0.38
    stell
    0.38
    Activations Density 0.004%

    No Known Activations