© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82604
    Prev
    Next
    INDEX
    Explanations

    presence

    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
    {
    0.86
     in
    0.85
    a
    0.80
    ä
    0.73
    ص
    0.70
     an
    0.68
    도
    0.67
    ان
    0.66
    an
    0.66
    ס
    0.66
    POSITIVE LOGITS
     presence
    1.16
     présence
    1.14
     наличие
    1.12
     presenza
    1.11
     aanwezig
    1.06
    presence
    1.05
    Presence
    1.05
     मौजूदगी
    0.98
     Presence
    0.96
     presença
    0.96
    Activations Density 0.043%

    No Known Activations