© 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. 57069
    Prev
    Next
    INDEX
    Explanations

    specifics following "that"

    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
    δες
    -1.48
    炱
    -1.48
    ÇÕES
    -1.47
     السياسية
    -1.42
     woes
    -1.41
     bidra
    -1.40
    钮
    -1.40
     Pandemie
    -1.38
     problemet
    -1.37
     bús
    -1.36
    POSITIVE LOGITS
     particular
    2.78
     same
    2.05
     one
    1.71
     exact
    1.63
     kind
    1.59
     Particular
    1.48
    particular
    1.48
     very
    1.46
     specific
    1.45
     tiny
    1.45
    Activations Density 0.059%

    No Known Activations