© 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. 73889
    Prev
    Next
    INDEX
    Explanations

    type of

    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
     azonban
    -1.71
    となり
    -1.45
     kuitenkin
    -1.45
     echter
    -1.44
    を行い
    -1.42
     ilustrasi
    -1.41
     있으며
    -1.40
     zwar
    -1.38
    だけではなく
    -1.38
     этих
    -1.34
    POSITIVE LOGITS
    ).
    1.77
     it
    1.70
    there
    1.64
     their
    1.47
     its
    1.46
    ”.
    1.44
     there
    1.42
    }$.
    1.39
    ’.
    1.32
     therein
    1.30
    Activations Density 0.168%

    No Known Activations