© 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. 174750
    Prev
    Next
    INDEX
    Explanations

    make jokes

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

    unrealistic expectations, deprecated, gone

    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
    ل
    0.63
    スタ
    0.55
    ان
    0.55
    아
    0.54
    l
    0.52
    Inspired
    0.52
    Right
    0.50
     Appear
    0.50
    APPE
    0.50
    ر
    0.50
    POSITIVE LOGITS
     sea
    0.48
     discovers
    0.47
    ceğiz
    0.47
     Paryayvachi
    0.46
     hydropower
    0.46
     hydrate
    0.46
     hyd
    0.45
     predicts
    0.44
    ږئ
    0.44
    rops
    0.44
    Activations Density 0.001%

    No Known Activations