© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138801
    Prev
    Next
    INDEX
    Explanations

    usually a, preferred the

    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
    ิจ
    0.44
     fetches
    0.44
     ejec
    0.43
    盾
    0.43
     armour
    0.43
     rač
    0.41
     diamant
    0.41
     abstracto
    0.40
     tathapi
    0.40
     choroby
    0.40
    POSITIVE LOGITS
    m
    0.54
     উল্লেখ
    0.54
     Yên
    0.50
    ina
    0.48
    شهر
    0.46
    ColumnKind
    0.46
    tsi
    0.45
    tell
    0.45
    𝗠
    0.44
    伉
    0.44
    Activations Density 0.001%

    No Known Activations