© 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. 100217
    Prev
    Next
    INDEX
    Explanations

    for example

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

    asking for help or advice

    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
     unver
    0.50
     imposs
    0.47
     merit
    0.46
     lactic
    0.45
     ar
    0.44
     outlandish
    0.44
     du
    0.43
    /****
    0.42
     unbelievable
    0.42
     bâ
    0.42
    POSITIVE LOGITS
    CharCode
    0.46
    Neurons
    0.45
     संबंधों
    0.44
    Friend
    0.44
    吃饭
    0.44
    Relations
    0.43
    Channels
    0.42
    physiology
    0.42
    Expanding
    0.42
    ▷
    0.42
    Activations Density 0.001%

    No Known Activations