© 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. 66559
    Prev
    Next
    INDEX
    Explanations

    in, In, Raise

    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
     of
    -1.36
     but
    -1.23
     where
    -1.20
     their
    -1.12
     by
    -1.10
    更に
    -1.10
    蜗
    -1.07
    噤
    -1.07
    哽
    -1.05
    ↵↵
    -1.03
    POSITIVE LOGITS
     byste
    1.61
     zvíř
    1.34
     ľudí
    1.32
    Unmanaged
    1.31
     německ
    1.30
     zimní
    1.27
     poliuret
    1.27
     szczeg
    1.27
     jednost
    1.23
    archiviato
    1.22
    Activations Density 0.000%

    No Known Activations