© 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. 123917
    Prev
    Next
    INDEX
    Explanations

    legal documents and projects

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

    various languages and topics

    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
    ALWAYS
    0.55
    ড
    0.47
    {$
    0.45
    +$
    0.44
     messes
    0.44
     প্লা
    0.43
    When
    0.43
    {
    0.43
    ט
    0.42
    LPTMR
    0.42
    POSITIVE LOGITS
     Grundlagen
    0.47
     Voj
    0.46
     Dienst
    0.45
    rocities
    0.45
     Spaß
    0.44
     Jego
    0.44
     দুইটি
    0.44
     Freude
    0.42
     Beweg
    0.42
    ungi
    0.42
    Activations Density 0.001%

    No Known Activations