© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102739
    Prev
    Next
    INDEX
    Explanations

    configuration items and properties

    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
     acreditar
    -1.20
     disgruntled
    -1.17
    establishing
    -1.12
     ausreichend
    -1.12
     mindestens
    -1.11
    CIUDAD
    -1.11
     arrivée
    -1.10
     fabulous
    -1.10
    大致
    -1.09
     tämän
    -1.09
    POSITIVE LOGITS
     in
    2.31
     that
    1.86
     which
    1.82
     on
    1.48
     for
    1.40
     from
    1.35
     with
    1.22
     of
    1.21
     created
    1.19
     like
    1.16
    Activations Density 0.982%

    No Known Activations