© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54940
    Prev
    Next
    INDEX
    Explanations

    starting or democracy

    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
     grotesque
    0.47
    ဉ်
    0.45
    န
    0.45
    нис
    0.44
    κο
    0.42
    物体
    0.42
     marvellous
    0.42
     integrable
    0.41
     تصمیم
    0.41
     छन्
    0.41
    POSITIVE LOGITS
    Vinyl
    0.50
     lakhs
    0.48
    洴
    0.46
    Fan
    0.46
    홧
    0.45
     odlič
    0.45
     Keep
    0.45
     Reinforced
    0.44
     kaisi
    0.44
     Lakh
    0.44
    Activations Density 0.017%

    No Known Activations