© 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. 190558
    Prev
    Next
    INDEX
    Explanations

    breaking it down

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

    alphanumeric codes and soothing phrases

    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
     Golf
    0.54
    ady
    0.52
     tenant
    0.52
     golf
    0.50
     recipient
    0.47
     ipad
    0.47
     i
    0.46
     senator
    0.46
    eres
    0.45
    asko
    0.45
    POSITIVE LOGITS
    وک
    0.58
    Კ
    0.56
     これは
    0.55
    இந்த
    0.53
    د
    0.53
    𝚃
    0.53
     Netzwerk
    0.53
     ܗܘ
    0.53
     Κα
    0.52
    போக்கு
    0.52
    Activations Density 0.000%

    No Known Activations