© 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. 185185
    Prev
    Next
    INDEX
    Explanations

    material/capacity descriptions

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

    accountability ensures, vital for

    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
    ý
    0.51
    c
    0.48
    q
    0.47
    Synopsis
    0.46
    Charged
    0.46
    ctu
    0.45
    füh
    0.45
    defined
    0.45
    u
    0.44
    f
    0.44
    POSITIVE LOGITS
     tubercul
    0.59
     크
    0.53
     prostagland
    0.52
     fibrils
    0.50
     diplomas
    0.50
     superfluid
    0.49
     バー
    0.49
     epig
    0.48
    」。
    0.48
     parton
    0.48
    Activations Density 0.000%

    No Known Activations