© 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. 135904
    Prev
    Next
    INDEX
    Explanations

    your digital consulting startup

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

    customer client account

    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
    衙
    0.49
    ギ
    0.46
    悝
    0.46
    ாது
    0.46
    evším
    0.45
    Productos
    0.45
    ﾖ
    0.44
    amnt
    0.43
    밥
    0.43
    ﾗ
    0.43
    POSITIVE LOGITS
     customer
    0.50
     accelerometer
    0.50
     Questionnaire
    0.49
     diversi
    0.49
     onboarding
    0.49
     hostname
    0.49
     cliente
    0.48
     client
    0.47
     notebook
    0.47
     startup
    0.47
    Activations Density 0.000%

    No Known Activations