© 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. 152467
    Prev
    Next
    INDEX
    Explanations

    dangerous followed by negative context

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

    why did the x cross the road joke

    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
     IMC
    0.46
     शाळे
    0.44
     celebrations
    0.44
     lyr
    0.42
     ++)
    0.41
    pc
    0.41
    nurse
    0.41
     通勤
    0.41
    lc
    0.41
    legte
    0.41
    POSITIVE LOGITS
    鶉
    0.48
    Disabled
    0.47
    ethereum
    0.47
    的這個
    0.46
    铵
    0.46
     diễn
    0.45
    queous
    0.45
    Backed
    0.45
    MovieDetails
    0.45
    MouseButton
    0.45
    Activations Density 0.002%

    No Known Activations