© 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. 16721
    Prev
    Next
    INDEX
    Explanations

    actions and their consequences/objects

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

    action verbs and outcomes

    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
    f
    0.69
     in
    0.64
    b
    0.63
    <0x80>
    0.61
     {
    0.55
    j
    0.55
     delle
    0.52
    fahren
    0.50
     \
    0.50
     في
    0.50
    POSITIVE LOGITS
    able
    0.94
    ings
    0.90
    者が
    0.71
    者
    0.71
    िंग
    0.70
    ers
    0.70
    ABLE
    0.68
    INGS
    0.67
    者は
    0.66
    િંગ
    0.64
    Activations Density 0.331%

    No Known Activations