© 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. 224513
    Prev
    Next
    INDEX
    Explanations

    a/any/your/of

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

    understanding concepts and communication

    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
     Import
    0.49
     Femme
    0.49
     Hazel
    0.48
     Ordin
    0.47
     Assertion
    0.47
     Hap
    0.46
    揩
    0.46
    ontan
    0.45
     Cassandra
    0.45
    testimonial
    0.45
    POSITIVE LOGITS
    けば
    0.52
     berdiri
    0.46
     bulun
    0.45
    ینا
    0.45
    ؔ
    0.44
    ม่า
    0.44
    ള്ള
    0.43
     ایران
    0.42
    கு
    0.41
     நிலையம்
    0.41
    Activations Density 0.000%

    No Known Activations