© 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. 204186
    Prev
    Next
    INDEX
    Explanations

    exercise or listening

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

    difference, very, counter, potassium, convincing

    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
    dll
    0.54
    y
    0.47
    allen
    0.46
    yl
    0.46
    ver
    0.45
     Height
    0.45
    mt
    0.44
     G
    0.44
    yuk
    0.44
    不易
    0.44
    POSITIVE LOGITS
     કર્મચારી
    0.52
     propagator
    0.50
    ਲ
    0.50
    ༦
    0.48
     कर्मचारी
    0.48
    𝓷
    0.48
     stringent
    0.47
    ܵ
    0.47
     effectuer
    0.46
     drastic
    0.45
    Activations Density 0.000%

    No Known Activations