© 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. 123841
    Prev
    Next
    INDEX
    Explanations

    shape, size, dimension description

    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
     مسلمانوں
    0.42
    忠
    0.41
     ลอง
    0.39
     என்பத
    0.39
    装
    0.39
     의미
    0.38
    使用了
    0.38
    到底
    0.38
    tanto
    0.38
    ﯿ
    0.38
    POSITIVE LOGITS
     semelhantes
    0.48
     apapun
    0.43
    0.42
     riddled
    0.40
     différente
    0.40
     $<
    0.39
     serupa
    0.39
    CHE
    0.38
     identiques
    0.38
    ankind
    0.38
    Activations Density 0.048%

    No Known Activations