© 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. 99541
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

    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
     from
    -1.18
     helped
    -1.17
     because
    -1.16
     so
    -1.15
     not
    -1.13
     or
    -1.11
     in
    -1.11
     that
    -1.11
     on
    -1.09
     sehr
    -1.09
    POSITIVE LOGITS
    different
    1.31
    during
    1.26
     différentes
    1.24
    several
    1.19
     streamlining
    1.18
     différents
    1.18
    usually
    1.14
    
    1.14
    érale
    1.14
    mainly
    1.13
    Activations Density 0.001%

    No Known Activations