© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185604
    Prev
    Next
    INDEX
    Explanations

    message bar

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

    simple options and appointments

    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
    Negative Logits
     tumor
    0.46
    照射
    0.46
    膨
    0.45
    Khokhlov
    0.43
    辎
    0.42
    矯正
    0.42
     escalas
    0.41
     toxicity
    0.40
    蟹
    0.40
     hoses
    0.40
    POSITIVE LOGITS
     zugleich
    0.54
     programme
    0.51
    ouse
    0.51
     outre
    0.50
    𝙚
    0.49
    ịa
    0.48
    érique
    0.47
     odmah
    0.46
    ere
    0.46
     wykorzyst
    0.46
    Activations Density 0.000%

    No Known Activations