© 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. 188951
    Prev
    Next
    INDEX
    Explanations

    links and URLs

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

    YouTube platform control

    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
    m
    0.54
     and
    0.53
    c
    0.52
     me
    0.51
     bio
    0.50
    rim
    0.50
    ro
    0.49
    z
    0.48
     bub
    0.47
    an
    0.47
    POSITIVE LOGITS
     présence
    0.57
     permesso
    0.55
     presencia
    0.54
     سپورټ
    0.54
     إذا
    0.54
     Ál
    0.53
     edificio
    0.52
     externos
    0.52
     vorhanden
    0.51
     عندما
    0.51
    Activations Density 0.000%

    No Known Activations