© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1815
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
     at
    -1.33
     when
    -1.26
     until
    -1.20
     from
    -1.20
     ilustracji
    -1.19
     without
    -1.16
     using
    -1.16
     or
    -1.14
     during
    -1.13
     some
    -1.09
    POSITIVE LOGITS
    ឪ
    1.21
     dreadful
    1.19
     aga
    1.19
    iniest
    1.16
     …..
    1.15
     !.
    1.14
     ____________
    1.13
    だけでなく
    1.12
     ___________
    1.09
     ,.
    1.08
    Activations Density 0.000%

    No Known Activations