© 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. 16-GEMMASCOPE-2-RES-262K
    7. 9477
    Prev
    Next
    INDEX
    Explanations

    what has been heard

    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_16_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
    م
    1.24
     It
    1.17
    ᱐
    1.06
    anın
    1.05
    но
    1.04
    ம்
    1.03
     மிசோ
    1.02
    ０
    1.02
    ется
    1.02
    ي
    0.99
    POSITIVE LOGITS
    8
    1.86
    2
    1.68
    5
    1.57
    3
    1.52
    9
    1.48
    6
    1.46
    र
    1.33
     heard
    1.26
    7
    1.25
     hear
    1.23
    Activations Density 0.012%

    No Known Activations