© 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. 17800
    Prev
    Next
    INDEX
    Explanations

    general categories or abstract concepts

    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
     a
    0.62
    <0xA1>
    0.53
    Capital
    0.49
    A
    0.48
    capital
    0.46
    এ
    0.44
    ка
    0.43
    ανα
    0.41
    ᱾
    0.41
    ك
    0.40
    POSITIVE LOGITS
    ContextCompat
    0.52
    সহ
    0.49
     včetně
    0.48
     ನಂತರ
    0.47
     vyn
    0.46
     jälkeen
    0.45
     Freiheit
    0.45
     عليه
    0.44
     తరువాత
    0.44
     dals
    0.44
    Activations Density 0.001%

    No Known Activations