© 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. 245571
    Prev
    Next
    INDEX
    Explanations

    specific names and titles

    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
    ance
    0.52
    lad
    0.46
    entes
    0.46
     squaring
    0.45
     कंपनी
    0.45
    R
    0.45
    ո
    0.44
    anya
    0.42
     വ
    0.42
    ered
    0.41
    POSITIVE LOGITS
     Origami
    0.53
     ciclo
    0.51
     Piaget
    0.48
    壹章
    0.48
     Rocky
    0.47
     Survivor
    0.47
     Allergy
    0.47
     მიმო
    0.46
     pierwszym
    0.46
     ஆசிரியர்
    0.46
    Activations Density 0.000%

    No Known Activations