© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101081
    Prev
    Next
    INDEX
    Explanations

    abandoned, cleansing, return

    np_acts-logits-general · gemini-2.5-flash-lite

    seriously?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vse
    0.52
     "
    0.50
    Bengal
    0.50
    👌
    0.50
     utf
    0.48
     anty
    0.46
    arlal
    0.46
     homely
    0.45
    tolerant
    0.45
     tolerant
    0.45
    POSITIVE LOGITS
     品質
    0.50
    որ
    0.49
     関
    0.48
     金属
    0.47
     み
    0.47
    removed
    0.46
    ობას
    0.46
     rinsing
    0.46
     있고
    0.46
     層
    0.46
    Activations Density 0.001%

    No Known Activations