Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169656
    Prev
    Next
    INDEX
    Explanations

    approach is

    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
    <tr>
    0.47
     پھ
    0.45
    enemy
    0.45
    *,
    0.44
    ANTED
    0.44
    stage
    0.43
     overcrow
    0.43
     respectively
    0.43
     introduce
    0.43
    <0x00>
    0.42
    POSITIVE LOGITS
    पणे
    0.48
    utam
    0.45
     shopping
    0.44
     இதன
    0.43
     ordination
    0.42
    願意
    0.42
    bells
    0.42
    ंसाठी
    0.42
    勍
    0.42
     Pemerintah
    0.41
    Activations Density 0.002%

    No Known Activations