© 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. 8514
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions and alternatives

    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
    Credential
    0.33
     أس
    0.32
    <0xEE>
    0.29
     invest
    0.29
     creación
    0.29
     przede
    0.29
    芮
    0.29
    Keyboard
    0.29
    servlet
    0.29
     irradiation
    0.29
    POSITIVE LOGITS
     ხოლო
    0.66
     natomiast
    0.59
     hingegen
    0.59
     나머
    0.58
    वहीं
    0.55
    而
    0.53
     वहीं
    0.50
     Sedangkan
    0.49
     Meanwhile
    0.49
     बाकी
    0.49
    Activations Density 0.320%

    No Known Activations