© 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. 216024
    Prev
    Next
    INDEX
    Explanations

    Lego bricks, temperature, child

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

    file db country details creator

    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
    象
    0.46
    কি
    0.46
    ৎস্য
    0.45
    лива
    0.45
    RECEIVED
    0.44
    制度
    0.44
    რძ
    0.44
    佣
    0.44
     ngôn
    0.43
    ရိ
    0.43
    POSITIVE LOGITS
    heti
    0.51
    jol
    0.51
    jährige
    0.50
    jat
    0.49
    år
    0.49
    at
    0.48
    ni
    0.48
    mes
    0.47
    jaz
    0.47
    ine
    0.46
    Activations Density 0.000%

    No Known Activations