© 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. 5011
    Prev
    Next
    INDEX
    Explanations

    keywords indicating requests or classifications

    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
    .
    0.45
    content
    0.44
    action
    0.43
    và
    0.43
    array
    0.43
    l
    0.43
    text
    0.41
    media
    0.41
     परंतु
    0.41
    act
    0.40
    POSITIVE LOGITS
     של
    0.49
    ՝
    0.46
     lainnya
    0.43
     기타
    0.43
     के
    0.43
     від
    0.43
    ⤠
    0.43
     altri
    0.41
     სხვა
    0.41
     ofApp
    0.39
    Activations Density 0.254%

    No Known Activations