© 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. 239785
    Prev
    Next
    INDEX
    Explanations

    Hockney, tube size, ion engine

    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
    width
    0.52
    assistant
    0.49
     स्पीकर
    0.46
     minutes
    0.45
    speaker
    0.45
     us
    0.44
    monium
    0.44
     suede
    0.43
    ñ
    0.43
    comm
    0.43
    POSITIVE LOGITS
     afgelopen
    0.46
    ўні
    0.46
    告
    0.46
     తెలుగు
    0.46
    㠻
    0.46
    োক
    0.45
     Kini
    0.45
     Einige
    0.45
    当たり
    0.44
    㥉
    0.44
    Activations Density 0.001%

    No Known Activations