© 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. 228262
    Prev
    Next
    INDEX
    Explanations

    medical and aquatic contexts

    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
    Կ
    0.54
    तू
    0.47
    Kinds
    0.47
    ാ
    0.46
    츰
    0.44
    Except
    0.44
    引起的
    0.44
    ோவில்
    0.43
    证实
    0.43
    Ꭺ
    0.43
    POSITIVE LOGITS
     formidable
    0.53
     seawater
    0.45
     [
    0.45
    ected
    0.45
     cancers
    0.45
     submarine
    0.44
     \{\
    0.44
     kompet
    0.43
     \{
    0.42
     delanter
    0.42
    Activations Density 0.000%

    No Known Activations