© 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. 112527
    Prev
    Next
    INDEX
    Explanations

    trade balance

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

    Constant value, specific actions, code structures

    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
     ຫຼື
    0.52
    rotl
    0.49
     đổ
    0.49
    rtl
    0.47
     标准
    0.46
     với
    0.46
    ρο
    0.46
     급
    0.46
     పై
    0.46
    rä
    0.45
    POSITIVE LOGITS
     sadness
    0.49
     Facebook
    0.44
     осе
    0.44
    iness
    0.44
     ведь
    0.44
     таки
    0.44
     consigui
    0.43
     perseverance
    0.42
     офі
    0.42
     குறைவாக
    0.42
    Activations Density 0.000%

    No Known Activations