© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10364
    Prev
    Next
    INDEX
    Explanations

    verbs of saying or reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_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
     =
    1.77
     または
    1.47
     or
    1.45
     love
    1.38
     +
    1.34
     romance
    1.34
     किंवा
    1.29
     არის
    1.24
     ή
    1.24
     ឬ
    1.24
    POSITIVE LOGITS
     reiterated
    1.71
    गौरतलब
    1.65
     sectoral
    1.61
    述べ
    1.54
     další
    1.51
     urged
    1.51
     государственный
    1.50
     reiter
    1.48
     rekao
    1.48
     محمد
    1.47
    Activations Density 0.001%

    No Known Activations