© 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. 65784
    Prev
    Next
    INDEX
    Explanations

    news and technical terms

    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
     Shig
    0.41
     compactly
    0.40
     वाला
    0.38
    벡
    0.37
     modulation
    0.37
     Sword
    0.37
    Ś
    0.37
     모델
    0.37
    Sword
    0.36
    subequations
    0.36
    POSITIVE LOGITS
     filing
    0.40
    खबर
    0.40
     Coach
    0.40
     attn
    0.39
     fil
    0.39
     ख़बर
    0.39
    fil
    0.38
    Coach
    0.38
     اجرای
    0.38
    opening
    0.37
    Activations Density 0.116%

    No Known Activations