© 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. 22-GEMMASCOPE-RES-131K
    7. 65376
    Prev
    Next
    INDEX
    Explanations

    degree of comparisons

    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_22/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
     invitaciones
    -1.35
    鯪
    -1.31
     slightly
    -1.27
     huellas
    -1.27
     convencer
    -1.24
     negociaciones
    -1.22
     generado
    -1.21
     sufficiently
    -1.21
     búsquedas
    -1.21
    轶
    -1.20
    POSITIVE LOGITS
     than
    1.63
     in
    1.59
     it
    1.20
     jauh
    1.12
     
    1.11
     I
    1.10
     остальных
    1.08
    Whereas
    1.05
     of
    1.02
    尤其是
    1.02
    Activations Density 0.038%

    No Known Activations