© 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. 26510
    Prev
    Next
    INDEX
    Explanations

    months days of the week and years

    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
     in
    -1.89
     into
    -1.40
     across
    -1.29
     of
    -1.16
     at
    -1.11
     on
    -1.10
     throughout
    -1.06
     from
    -1.03
     within
    -1.02
     στο
    -1.02
    POSITIVE LOGITS
    where
    1.19
    Erstellt
    1.02
    Če
    1.00
     pneumo
    0.98
    Når
    0.98
     noro
    0.96
     plafon
    0.95
     terce
    0.95
     expédi
    0.94
     expor
    0.94
    Activations Density 0.087%

    No Known Activations