© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18928
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.45
     front
    0.44
    ArrayList
    0.43
    1
    0.43
     rulers
    0.42
    特
    0.42
    IO
    0.42
    Constraints
    0.40
    SP
    0.40
    Parameter
    0.39
    POSITIVE LOGITS
     आणि
    0.62
    и
    0.60
     և
    0.58
     ಮತ್ತು
    0.56
     и
    0.55
    ratulations
    0.55
    এবং
    0.54
     nhưng
    0.54
     және
    0.54
     અને
    0.54
    Activations Density 0.009%

    No Known Activations