© 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-65K
    7. 968
    Prev
    Next
    INDEX
    Explanations

    quote-worthy statements

    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_65k_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
    ۔
    0.41
     Bernie
    0.41
    客厅
    0.40
     Washington
    0.39
     w
    0.39
     ребята
    0.38
    <td>
    0.38
    ã
    0.38
     Vespa
    0.38
     wohn
    0.38
    POSITIVE LOGITS
    medallas
    0.52
    జేపీ
    0.51
    THz
    0.51
     inclinations
    0.48
    щика
    0.48
    jewelry
    0.47
    Organic
    0.47
    Async
    0.47
    חות
    0.47
     intestate
    0.47
    Activations Density 0.000%

    No Known Activations