© 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. 17266
    Prev
    Next
    INDEX
    Explanations

    by type

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

    foreshadows suicide Signals Typical stride variable

    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
    atus
    0.47
     atualmente
    0.46
    inizi
    0.45
    atians
    0.45
    us
    0.45
    ës
    0.45
    竭
    0.45
    ंग
    0.44
     Robbins
    0.44
     निच
    0.44
    POSITIVE LOGITS
     ae
    0.52
    dimethyl
    0.51
     ukl
    0.48
     ईमित्र
    0.46
     だ
    0.46
     fontWeight
    0.46
     eh
    0.45
     змо
    0.45
     formulae
    0.45
    renderCamera
    0.45
    Activations Density 0.000%

    No Known Activations