© 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. 53-GEMMASCOPE-2-RES-262K
    7. 9919
    Prev
    Next
    INDEX
    Explanations

    gemma.dev/gemma

    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_53_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
     J
    0.43
    ताल
    0.43
    тельной
    0.42
     मोह
    0.41
     मुह
    0.40
     وجه
    0.39
    ުން
    0.38
     ج
    0.37
     двой
    0.37
    Moj
    0.37
    POSITIVE LOGITS
     G
    0.62
     g
    0.53
     گ
    0.52
     ग
    0.49
     Cal
    0.47
     г
    0.46
    G
    0.43
    psc
    0.41
     Lucas
    0.41
     গ
    0.40
    Activations Density 0.012%

    No Known Activations