© 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. 65895
    Prev
    Next
    INDEX
    Explanations

    academic study or code token

    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
     will
    -1.53
     it
    -1.20
     not
    -1.13
     There
    -1.13
     get
    -1.11
     what
    -1.11
     how
    -1.08
     In
    -1.06
    R
    -1.05
     did
    -1.05
    POSITIVE LOGITS
     plafon
    1.59
     ſou
    1.45
     bascul
    1.37
     própri
    1.35
     素描
    1.34
     materie
    1.34
    Terima
    1.34
     incrí
    1.31
    鸸
    1.30
     pè
    1.30
    Activations Density 0.001%

    No Known Activations