© 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. 156008
    Prev
    Next
    INDEX
    Explanations

    blows off, audit alone, time period

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

    escape codes and codes

    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
     त्यांनी
    0.52
     काँग्रेस
    0.50
     나왔
    0.48
    entuk
    0.47
     बताएं
    0.47
     больных
    0.46
     пропа
    0.46
     희
    0.45
     хирур
    0.45
     स्वयं
    0.45
    POSITIVE LOGITS
    師
    0.49
     ifs
    0.44
    orton
    0.41
    비를
    0.41
    ozz
    0.40
     intensity
    0.40
     Mous
    0.40
    ysing
    0.40
    ermes
    0.39
     intensities
    0.39
    Activations Density 0.000%

    No Known Activations