© 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. 66781
    Prev
    Next
    INDEX
    Explanations

    beta

    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
    ↵↵
    -3.11
    比如说
    -2.61
    躂
    -2.31
    啬
    -2.27
    sandália
    -2.17
    縂
    -2.14
    UGHTER
    -2.11
     dubbed
    -2.08
    聼
    -2.06
     fashioned
    -2.05
    POSITIVE LOGITS
    2
    3.84
    3
    3.06
    If
    2.91
    6
    2.80
    By
    2.67
    From
    2.64
    with
    2.63
    7
    2.61
    篥
    2.58
    }$
    2.52
    Activations Density 0.024%

    No Known Activations