© 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. 10-GEMMASCOPE-RES-131K
    7. 38839
    Prev
    Next
    INDEX
    Explanations

    interesado en, meio perdido

    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_10/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
     tumultuous
    -2.11
     gruesome
    -2.06
     delectable
    -2.05
     renowned
    -2.03
     fervent
    -2.00
     quintessential
    -1.98
     unbelievably
    -1.89
     insanely
    -1.87
     lauded
    -1.83
     flamboyant
    -1.83
    POSITIVE LOGITS
     or
    1.83
     on
    1.73
     and
    1.71
     includes
    1.68
     in
    1.59
     with
    1.54
     for
    1.52
     adds
    1.52
     offers
    1.52
     helps
    1.51
    Activations Density 0.007%

    No Known Activations