© 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. 194175
    Prev
    Next
    INDEX
    Explanations

    bed sores

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

    specific actions and their consequences

    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
    TEGER
    0.52
     Gans
    0.48
     Te
    0.48
     M
    0.48
     Sval
    0.48
     Si
    0.47
     Merton
    0.46
     cinci
    0.46
     ず
    0.45
     Q
    0.45
    POSITIVE LOGITS
    Among
    0.44
    Within
    0.44
     diversifying
    0.44
    robespierre
    0.42
     remarkably
    0.41
     بينهم
    0.41
     साउथ
    0.41
    ട്ടില്‍
    0.39
     angiogenic
    0.39
     Amongst
    0.39
    Activations Density 0.001%

    No Known Activations