© 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. 95319
    Prev
    Next
    INDEX
    Explanations

    listing positive amenities and features

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

    find the right fit

    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
     справо
    0.45
     явления
    0.44
    '`
    0.43
     attributing
    0.42
     mediator
    0.42
    efeu
    0.41
     adop
    0.41
    ంబే
    0.41
    himanyu
    0.40
     mercy
    0.40
    POSITIVE LOGITS
     લાભ
    0.46
     بالای
    0.45
    슈
    0.44
    ที่ดี
    0.44
    がいい
    0.44
     સારી
    0.43
     اچھی
    0.43
    塑造
    0.43
     ただ
    0.43
    ắm
    0.42
    Activations Density 0.000%

    No Known Activations