© 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. 222806
    Prev
    Next
    INDEX
    Explanations

    essential to, producing numerous

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

    changes following certain words

    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
     प्लांट्स
    0.60
     他们
    0.58
    植物
    0.56
     системой
    0.55
    ült
    0.54
    Ζ
    0.54
    சூ
    0.53
    锑
    0.53
     unido
    0.53
    他们
    0.52
    POSITIVE LOGITS
     pH
    0.50
     hide
    0.46
     fragile
    0.45
     peel
    0.44
     diffuse
    0.44
     brow
    0.44
     touch
    0.44
     tennis
    0.43
     kWh
    0.43
     micro
    0.42
    Activations Density 0.000%

    No Known Activations