© 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. 17207
    Prev
    Next
    INDEX
    Explanations

    abstract or formal 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
    кли
    0.47
    faction
    0.46
    nG
    0.46
     Ι
    0.45
     poch
    0.45
     Σ
    0.44
    oxing
    0.44
    net
    0.44
    log
    0.42
    ográficas
    0.42
    POSITIVE LOGITS
    禅
    0.52
    ទំនាក់ទំនង
    0.50
    閱讀
    0.45
    縁
    0.45
     adsorb
    0.44
    楹
    0.43
     المراجعه
    0.42
    殖
    0.42
    砓
    0.42
    妽
    0.42
    Activations Density 0.006%

    No Known Activations