© 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. 16-GEMMASCOPE-2-RES-262K
    7. 137916
    Prev
    Next
    INDEX
    Explanations

    Amendments, Fama-French, Upanishads, Communist Party

    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_16_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
     (
    0.65
     Transaction
    0.56
     Stores
    0.52
     Ranking
    0.52
     Deduction
    0.52
     ED
    0.51
     músico
    0.51
     UNION
    0.50
     UI
    0.50
    l
    0.50
    POSITIVE LOGITS
    ات
    0.60
     የተቀ
    0.59
    ат
    0.54
     плат
    0.53
    StubCompat
    0.52
     eingerichtet
    0.52
     patterned
    0.52
    𝙜
    0.51
     imprinted
    0.50
    aments
    0.50
    Activations Density 0.000%

    No Known Activations