© 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. 73303
    Prev
    Next
    INDEX
    Explanations

    addition to a previous statement

    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
     this
    -1.29
     those
    -1.16
     their
    -1.11
     these
    -1.08
     its
    -1.08
    仍
    -1.07
     ataques
    -1.02
     which
    -1.02
     that
    -1.01
     it
    -0.97
    POSITIVE LOGITS
     also
    2.59
     også
    1.38
     также
    1.38
     também
    1.34
     גם
    1.32
     همچنین
    1.30
    也很
    1.23
     أيضًا
    1.23
     myös
    1.20
     moreover
    1.18
    Activations Density 0.033%

    No Known Activations