© 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. 75080
    Prev
    Next
    INDEX
    Explanations

    toast and toaster

    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
    ?’
    -2.41
    三天
    -2.30
    ised
    -2.30
    都不是
    -2.22
    就像是
    -2.20
     cyclone
    -2.20
     THIS
    -2.20
    ꪹ
    -2.14
     pero
    -2.13
    üğü
    -2.11
    POSITIVE LOGITS
    {
    2.80
    }
    2.39
    sandalia
    2.23
     Its
    2.13
    ated
    2.09
    他现在
    2.06
    这件事情
    2.05
    珝
    2.05
    ⃚
    1.98
    ``
    1.93
    Activations Density 0.003%

    No Known Activations