© 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. 28327
    Prev
    Next
    INDEX
    Explanations

    controlling inputs and outputs

    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
    סים
    0.44
    ignez
    0.42
     improper
    0.42
    ির
    0.40
     teljesen
    0.40
     heel
    0.40
    ⅱ
    0.39
    ikannya
    0.39
     boyfriend
    0.39
     పూర్తిగా
    0.39
    POSITIVE LOGITS
    gold
    0.44
    ocus
    0.41
    table
    0.41
    Example
    0.41
    #>
    0.40
    modal
    0.39
     Author
    0.38
    Examples
    0.38
    matic
    0.38
     वर्णित
    0.38
    Activations Density 0.001%

    No Known Activations