© 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. 55140
    Prev
    Next
    INDEX
    Explanations

    future events or performances

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

    Agent/Assistant dialogue roles

    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
     additional
    0.42
    modulo
    0.40
     intermediate
    0.40
     incon
    0.39
    %=
    0.39
    additional
    0.39
    convolve
    0.39
    }=
    0.39
    intermediate
    0.38
    flat
    0.38
    POSITIVE LOGITS
    BURG
    0.50
    GLAND
    0.46
    তর
    0.45
    적이
    0.43
    ÁN
    0.42
     नीतियों
    0.41
     ज़कात
    0.40
    တတ်
    0.39
     Mondiale
    0.39
     Borrower
    0.39
    Activations Density 0.000%

    No Known Activations