© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92545
    Prev
    Next
    INDEX
    Explanations

    code structures and elements

    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
     after
    -1.59
     at
    -1.46
     with
    -1.25
     despite
    -1.19
     whose
    -1.19
     does
    -1.16
     before
    -1.16
     without
    -1.16
     there
    -1.16
     like
    -1.15
    POSITIVE LOGITS
    1.55
        
    1.31
     situés
    1.18
    ＇
    1.18
    HUMAN
    1.16
     exhilarating
    1.13
     insanely
    1.12
     molti
    1.12
     miro
    1.09
     acclaimed
    1.08
    Activations Density 0.016%

    No Known Activations