© 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. 176373
    Prev
    Next
    INDEX
    Explanations

    existing wellness

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

    bioavailability, balance increases

    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
    result
    0.52
    òa
    0.48
    sar
    0.45
    holiday
    0.45
    ?\\
    0.45
    Ӏ
    0.45
    neither
    0.45
     Pass
    0.43
    remain
    0.43
    ⚖
    0.42
    POSITIVE LOGITS
     spezif
    0.51
     fünf
    0.50
     psychotic
    0.50
    菪
    0.49
     douze
    0.49
     siglas
    0.48
     slou
    0.46
     campione
    0.45
    şti
    0.45
     খারাপ
    0.44
    Activations Density 0.000%

    No Known Activations