© 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. 166234
    Prev
    Next
    INDEX
    Explanations

    points, society, policy

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

    Tokyo, Asakusa, Senso-ji Temple

    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
     stiffness
    0.50
    strual
    0.49
     efectuar
    0.49
     stiff
    0.48
    ุ
    0.47
     persist
    0.47
     нашу
    0.47
     سامنے
    0.46
     നമ്മുടെ
    0.45
    ư
    0.45
    POSITIVE LOGITS
    edere
    0.52
    Política
    0.52
    睃
    0.48
    Nich
    0.47
    绞
    0.47
     Пла
    0.46
    Agu
    0.46
    Пла
    0.46
    ፈላ
    0.45
     Институт
    0.45
    Activations Density 0.000%

    No Known Activations