© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11227
    Prev
    Next
    INDEX
    Explanations

    example sentences, questions, or lists

    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
     its
    -1.55
     also
    -1.47
     with
    -1.43
    ʽ
    -1.36
    </i>
    -1.34
    ]}$
    -1.31
     different
    -1.30
     on
    -1.30
     their
    -1.29
     his
    -1.28
    POSITIVE LOGITS
    そういった
    1.55
    などが
    1.50
    <bos>
    1.45
    がありますが
    1.44
     maverick
    1.43
    などを
    1.42
    俨
    1.41
    があるので
    1.39
    tamento
    1.36
    こういった
    1.34
    Activations Density 0.001%

    No Known Activations