© 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. 22-GEMMASCOPE-RES-131K
    7. 15182
    Prev
    Next
    INDEX
    Explanations

    spatial and relational contexts

    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
     capucha
    -1.27
     manguera
    -1.25
     cremallera
    -1.24
     almohada
    -1.21
     mascarilla
    -1.17
     estufa
    -1.15
     wollt
    -1.13
     bañera
    -1.13
    Efter
    -1.12
     zewnętrzne
    -1.11
    POSITIVE LOGITS
     to
    3.98
     against
    2.27
     between
    2.11
     towards
    1.95
     from
    1.79
     into
    1.79
     for
    1.76
     toward
    1.68
     on
    1.61
     к
    1.41
    Activations Density 0.238%

    No Known Activations