© 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. 245242
    Prev
    Next
    INDEX
    Explanations

    games, these, watching, elite, end, now

    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
    🔞
    0.42
     ağır
    0.42
    ढा
    0.41
     emphasises
    0.40
    州
    0.40
    坯
    0.40
    有人
    0.40
     bào
    0.40
    insertBefore
    0.40
    ：《
    0.40
    POSITIVE LOGITS
     οποίο
    0.50
     влияние
    0.47
     ')')
    0.46
     buds
    0.45
    feas
    0.43
    )}^{\
    0.43
     ప్రయత్
    0.43
     எங்கள்
    0.43
     helix
    0.42
    ization
    0.42
    Activations Density 0.001%

    No Known Activations