© 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. 80748
    Prev
    Next
    INDEX
    Explanations

    visit www

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

    at [link or resource]

    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
    וד
    0.46
     ジャケット
    0.45
     '${
    0.40
     Ꭰ
    0.40
    𝜃
    0.40
     fractal
    0.39
     primarySwatch
    0.39
    projectile
    0.39
     blazer
    0.39
     gói
    0.39
    POSITIVE LOGITS
    ঃ
    0.45
    ：
    0.44
    aper
    0.43
    हरण
    0.43
    ravés
    0.41
    ologien
    0.40
    urangan
    0.39
    origines
    0.39
    It
    0.39
    eran
    0.38
    Activations Density 0.001%

    No Known Activations