© 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. 152377
    Prev
    Next
    INDEX
    Explanations

    subject plus state or location

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

    letters and color

    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
     trajectory
    0.47
     trajet
    0.47
    separ
    0.45
     fusing
    0.45
    ，
    0.43
     canals
    0.43
     dyslex
    0.42
    當中
    0.42
     canal
    0.42
     compact
    0.41
    POSITIVE LOGITS
    дони
    0.55
    EnglishMarks
    0.54
    UpperBound
    0.54
    TextureAsset
    0.52
     Herbs
    0.48
     বিশ্বাসের
    0.44
     tcpHeader
    0.44
    ковского
    0.44
    EndZ
    0.44
    え
    0.44
    Activations Density 0.000%

    No Known Activations