© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 197504
    Prev
    Next
    INDEX
    Explanations

    adding pictures, information

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

    familiar painting watercolor

    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
     다르
    0.46
     pok
    0.44
     pillar
    0.44
    rowse
    0.43
    liest
    0.42
    gle
    0.42
     s
    0.41
    ding
    0.41
    df
    0.41
    ram
    0.40
    POSITIVE LOGITS
    醎
    0.50
    妛
    0.49
    ኖች
    0.47
     Anne
    0.46
    Anne
    0.46
    संयुक्त
    0.46
     Canadá
    0.46
     कनाडा
    0.46
    ούς
    0.46
    Taylor
    0.45
    Activations Density 0.000%

    No Known Activations