© 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. 104585
    Prev
    Next
    INDEX
    Explanations

    participating in, to close

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

    contrast or continuation

    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
    :
    0.55
    测
    0.46
    ()
    0.44
     *
    0.43
    いわ
    0.43
     berupa
    0.41
     CR
    0.41
    感
    0.41
     Grit
    0.40
    Marker
    0.40
    POSITIVE LOGITS
     actuales
    0.55
     सध्या
    0.54
     பிரசா
    0.54
     membres
    0.50
    syscall
    0.50
     методы
    0.49
     დღ
    0.48
    <start_of_turn>
    0.48
     सदस्यों
    0.48
    <unused35>
    0.47
    Activations Density 0.001%

    No Known Activations