© 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. 3240
    Prev
    Next
    INDEX
    Explanations

    there exists a

    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
     qualquer
    -1.38
     qualsiasi
    -1.34
     cualquier
    -1.33
    任何
    -1.28
     any
    -1.26
     любом
    -1.23
     любой
    -1.08
    Any
    -1.07
     anything
    -1.03
     olabilir
    -1.02
    POSITIVE LOGITS
     a
    1.24
     integers
    1.09
     sequences
    1.02
     numbers
    1.00
     for
    0.99
     scalars
    0.97
    integer
    0.96
     unique
    0.96
     some
    0.94
    UNIQUE
    0.92
    Activations Density 0.041%

    No Known Activations