© 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. 136798
    Prev
    Next
    INDEX
    Explanations

    sequence of 8s

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

    988 Suicide & Crisis Lifeline

    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
     that
    1.36
    2
    1.31
    1
    1.15
    ٢
    1.15
    _
    1.09
    ع
    1.09
    ١
    1.09
     as
    1.08
    การ
    1.04
    تان
    1.04
    POSITIVE LOGITS
    in
    1.61
    ر
    1.22
    ानुसार
    1.13
    inni
    1.05
    inį
    1.03
    ם
    1.03
    нг
    0.99
    AndroidJUnit
    0.98
    ىڭ
    0.96
    ى
    0.96
    Activations Density 1.265%

    No Known Activations