© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66596
    Prev
    Next
    INDEX
    Explanations

    used for extended periods

    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
    -1.52
     there
    -1.48
     their
    -1.30
     from
    -1.23
     what
    -1.21
     some
    -1.20
     any
    -1.13
     these
    -1.12
     trattano
    -1.08
     so
    -1.06
    POSITIVE LOGITS
    Used
    1.25
     sés
    1.23
     použ
    1.20
    ೨
    1.20
     frequentemente
    1.18
    ใช้งาน
    1.15
    several
    1.14
    Uses
    1.13
     rosso
    1.13
     BORROW
    1.11
    Activations Density 0.019%

    No Known Activations