© 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. 117347
    Prev
    Next
    INDEX
    Explanations

    location and attributes

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

    two sentence

    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
    pix
    0.50
    mmol
    0.49
    既
    0.47
    rotating
    0.46
    一下
    0.45
    内
    0.45
    \(
    0.44
    wall
    0.44
    Wall
    0.44
    ъ
    0.44
    POSITIVE LOGITS
     sheds
    0.50
     ovens
    0.48
     Жу
    0.46
     Joz
    0.46
    𐰚
    0.46
     enshr
    0.45
     świad
    0.45
     suitors
    0.45
     perpetrated
    0.44
     shipments
    0.44
    Activations Density 0.001%

    No Known Activations