© 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-65K
    7. 36748
    Prev
    Next
    INDEX
    Explanations

    origin, color, wait, years, scores, variation, instructions

    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
    I
    0.48
     außer
    0.43
     anomalies
    0.42
     incongru
    0.42
     efficiently
    0.40
     absorption
    0.39
     emulsion
    0.39
     injection
    0.39
     calorie
    0.39
     insight
    0.39
    POSITIVE LOGITS
    к
    0.47
     trecut
    0.46
    𝙩
    0.45
     penggem
    0.45
    म
    0.45
    اويه
    0.44
    𝙨
    0.44
     deceduto
    0.44
     menunjukkan
    0.43
    樁
    0.42
    Activations Density 0.016%

    No Known Activations