© 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. 11104
    Prev
    Next
    INDEX
    Explanations

    Alibaba, Perry, refrigerators, Signature

    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
    -1.50
     your
    -1.40
     their
    -1.19
     such
    -1.11
     we
    -1.11
     of
    -1.07
     bądź
    -1.07
     We
    -1.05
     make
    -1.02
     koń
    -1.02
    POSITIVE LOGITS
    <bos>
    1.72
     épices
    1.34
    Makan
    1.34
    これは
    1.23
     bailarina
    1.22
    ímos
    1.21
     suscit
    1.21
     poliuret
    1.20
    ですが
    1.14
     pantalon
    1.14
    Activations Density 0.001%

    No Known Activations