© 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. 17188
    Prev
    Next
    INDEX
    Explanations

    candidates who

    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
    Ч
    0.52
     wipe
    0.46
     сосу
    0.46
     serveur
    0.46
     migrate
    0.45
     desloc
    0.45
     Қ
    0.44
     насыщен
    0.44
    ⵄ
    0.44
     années
    0.43
    POSITIVE LOGITS
    ed
    0.58
    va
    0.52
    ngram
    0.52
    r
    0.52
    otre
    0.49
    la
    0.48
    lang
    0.47
    gna
    0.46
    ng
    0.46
    max
    0.46
    Activations Density 0.006%

    No Known Activations