© 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. 31-GEMMASCOPE-2-RES-65K
    7. 53655
    Prev
    Next
    INDEX
    Explanations

    times, days, moments

    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
     einer
    0.54
     initial
    0.46
    års
    0.46
     nuisance
    0.45
     à
    0.44
     für
    0.44
     schw
    0.43
     eerste
    0.43
     werden
    0.42
     για
    0.42
    POSITIVE LOGITS
     সর্বদা
    0.48
    常に
    0.46
    ૪
    0.46
     poput
    0.46
     folhas
    0.45
    这段
    0.45
    ༞
    0.44
    を感じ
    0.44
     foglie
    0.44
     항상
    0.44
    Activations Density 0.004%

    No Known Activations