© 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. 241437
    Prev
    Next
    INDEX
    Explanations

    rewards, answers, or information

    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
     kojoj
    0.47
     Premiership
    0.44
     三
    0.44
     Instructions
    0.43
    酗
    0.43
    以下
    0.42
     goa
    0.42
    液
    0.42
     xx
    0.42
    二维
    0.42
    POSITIVE LOGITS
    ς
    0.60
    ный
    0.52
    се
    0.49
     stumbled
    0.49
     investigated
    0.49
    все
    0.49
    си
    0.49
    спи
    0.48
     queried
    0.47
    ждый
    0.47
    Activations Density 0.001%

    No Known Activations