© 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. 24576
    Prev
    Next
    INDEX
    Explanations

    specific phrases to topics

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

    understanding concepts

    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
    odyne
    0.43
     discursive
    0.43
    ↵
    0.42
    AV
    0.40
     perception
    0.40
     restoration
    0.39
     corrective
    0.38
     discriminatory
    0.38
     preferential
    0.38
    </i>
    0.38
    POSITIVE LOGITS
     ול
    0.64
     llevaba
    0.63
    ס
    0.54
    =\
    0.52
     beträgt
    0.50
    kotlin
    0.50
     hac
    0.49
     appelle
    0.48
    ")',
    0.48
     недостатки
    0.47
    Activations Density 0.000%

    No Known Activations