© 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. 128233
    Prev
    Next
    INDEX
    Explanations

    with a/an/his

    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
     or
    -1.30
     them
    -1.28
     each
    -1.24
     where
    -1.11
     CascadeType
    -1.10
     fact
    -1.09
     the
    -1.09
     our
    -1.08
     []:
    -1.07
     your
    -1.06
    POSITIVE LOGITS
     a
    1.96
     réfrig
    1.23
     médecin
    1.17
    違和感
    1.14
     encendido
    1.13
     лучший
    1.11
     pengobatan
    1.11
     faktiskt
    1.09
    何故
    1.08
    少々
    1.08
    Activations Density 0.035%

    No Known Activations