© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57472
    Prev
    Next
    INDEX
    Explanations

    .xenTue, 26 Sep 2017 21:56:59 GMTvBulletin60https://www.sencha.com/forum/images/misc/rss.pngSencha Forum -

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     some
    -0.71
     vídeo
    -0.71
     tulisan
    -0.68
     articulo
    -0.67
    sth
    -0.67
     begin
    -0.66
     summarized
    -0.66
     Rigby
    -0.65
     Galli
    -0.64
    ideo
    -0.63
    POSITIVE LOGITS
    adox
    0.71
    dox
    0.70
    Jahres
    0.66
    aturen
    0.65
     Ordo
    0.65
    Selon
    0.65
    EXPERIENCE
    0.64
     Mayr
    0.63
     Jaguar
    0.63
    alyse
    0.63
    Activations Density 0.050%

    No Known Activations