© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8424
    Prev
    Next
    INDEX
    Explanations

    prepositions (in, from, on)

    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_10/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
    letzt
    -1.33
    aaaaaa
    -1.24
     our
    -1.23
     använder
    -1.23
     fabia
    -1.22
    gegeben
    -1.22
     dacia
    -1.21
     malic
    -1.21
    meldung
    -1.20
     $\&$
    -1.19
    POSITIVE LOGITS
     It
    1.69
     For
    1.55
     recordar
    1.43
    The
    1.42
     is
    1.41
     new
    1.34
     Zuw
    1.33
     After
    1.32
     Keep
    1.32
     after
    1.27
    Activations Density 0.036%

    No Known Activations