© 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. 71137
    Prev
    Next
    INDEX
    Explanations

    physical and psychological states

    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
    ↵
    0.48
    mathrm
    0.48
    console
    0.47
    iled
    0.43
     majority
    0.43
     winery
    0.42
    igel
    0.42
    majority
    0.41
    ᱞ
    0.40
    iture
    0.40
    POSITIVE LOGITS
    อาการ
    0.50
    焲
    0.49
    ൬
    0.48
    ாதாரண
    0.46
     esteja
    0.46
    较高
    0.45
    ጤ
    0.45
    昅
    0.44
     그러면
    0.44
    较低
    0.43
    Activations Density 0.002%

    No Known Activations