© 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. 84639
    Prev
    Next
    INDEX
    Explanations

    contrasting negatives

    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
     தனது
    0.50
    ה
    0.49
    sixth
    0.47
     उनकी
    0.46
    ப்
    0.45
    rog
    0.44
    meas
    0.44
    пи
    0.44
     kulland
    0.44
    pathetic
    0.43
    POSITIVE LOGITS
    $-$,
    0.50
     $,
    0.47
     discounts
    0.46
     цены
    0.46
     rett
    0.46
     =
    0.45
    '$,
    0.45
    IntegerField
    0.44
     yeasts
    0.44
     oxidized
    0.44
    Activations Density 0.010%

    No Known Activations