© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33090
    Prev
    Next
    INDEX
    Explanations

    prepositions and locations

    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_22/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
     ausgesprochen
    -1.30
    seems
    -1.30
    appears
    -1.29
     puramente
    -1.26
    seemed
    -1.26
     rembourse
    -1.25
    삵
    -1.25
     toutefois
    -1.23
    appeared
    -1.22
     délais
    -1.22
    POSITIVE LOGITS
     of
    1.52
     and
    1.42
     different
    1.24
     in
    1.20
     using
    1.17
     generally
    1.14
     goes
    1.10
     as
    1.09
     think
    1.09
     went
    1.08
    Activations Density 0.003%

    No Known Activations