© 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. 142691
    Prev
    Next
    INDEX
    Explanations

    planning and steps

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

    codes and numbers

    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
    éci
    0.52
    SourceName
    0.49
    ጹ
    0.48
     formContext
    0.47
    ScriptObject
    0.46
    Tabpage
    0.46
     medicamento
    0.45
     médicaments
    0.45
    珞
    0.45
    ціа
    0.44
    POSITIVE LOGITS
    2
    0.63
    3
    0.59
    :
    0.55
     evidenced
    0.52
    7
    0.52
     yet
    0.52
     discounted
    0.52
    td
    0.51
    9
    0.51
     but
    0.50
    Activations Density 0.001%

    No Known Activations