© 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. 18928
    Prev
    Next
    INDEX
    Explanations

    ... followed by words

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

    joke punchlines explaining "because"

    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
    ↵↵
    0.66
    ↵↵↵↵
    0.45
    <th>
    0.45
     Schedule
    0.44
    IES
    0.44
     F
    0.43
    EY
    0.41
     Control
    0.41
     Estimated
    0.41
     CEL
    0.41
    POSITIVE LOGITS
    s
    0.64
    ratulations
    0.58
     whereupon
    0.54
     અને
    0.52
     avevo
    0.52
    и
    0.51
    そして
    0.50
     և
    0.50
    এবং
    0.49
     говорю
    0.49
    Activations Density 0.012%

    No Known Activations