© 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. 185932
    Prev
    Next
    INDEX
    Explanations

    Flex Cable, specialized training, renovation

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

    captivated or feel

    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
     процессов
    0.48
    «,
    0.47
    setVelocity
    0.46
    9
    0.46
    preventDefault
    0.45
    ocond
    0.43
    vede
    0.43
     modulo
    0.42
    divide
    0.42
     सांगतात
    0.42
    POSITIVE LOGITS
    Ⲩ
    0.60
    ܚ
    0.50
    ز
    0.50
    ΙΚ
    0.48
    ካ
    0.48
     designers
    0.47
    AIRMAN
    0.47
    یس
    0.46
    ק
    0.46
     bzw
    0.46
    Activations Density 0.001%

    No Known Activations