© 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. 196790
    Prev
    Next
    INDEX
    Explanations

    closest positions and adjacencies

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

    clear or close description

    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
    Warum
    0.61
    Ci
    0.52
    י
    0.50
    ك
    0.49
    惭
    0.47
    Why
    0.46
    އ
    0.46
    Yang
    0.46
    ת
    0.46
    Danke
    0.45
    POSITIVE LOGITS
     unison
    0.52
     fluidity
    0.48
     clearest
    0.47
     closeness
    0.47
     closest
    0.46
     crystal
    0.46
     renal
    0.44
     Crystal
    0.44
     regulation
    0.42
     synchron
    0.42
    Activations Density 0.001%

    No Known Activations