© 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. 205981
    Prev
    Next
    INDEX
    Explanations

    iPod interface

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

    what as

    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
    Not in Any Lists

    No Comments

    Negative Logits
    HELLO
    0.54
    HE
    0.52
    ACC
    0.51
    Acc
    0.48
     nip
    0.47
    KY
    0.47
     témo
    0.47
     c
    0.47
    GE
    0.47
    CE
    0.46
    POSITIVE LOGITS
     publicidad
    0.54
     基
    0.53
     或者
    0.50
     生活
    0.49
     стимули
    0.48
    <unused616>
    0.48
     Bereiche
    0.47
    ভেন
    0.46
     আনোয়ার
    0.46
     religión
    0.46
    Activations Density 0.000%

    No Known Activations