© 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. 409
    Prev
    Next
    INDEX
    Explanations

    forms, code structures, questions

    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
     TabLayout
    -1.15
    把它
    -1.13
     ProgressBar
    -1.12
    🦐
    -1.06
     fucking
    -0.99
     agence
    -0.97
     tourisme
    -0.95
    either
    -0.95
     $+
    -0.95
     either
    -0.95
    POSITIVE LOGITS
    タリア
    1.23
    ransition
    1.18
    Ẓ
    1.16
    Moh
    1.12
    }');
    1.12
    >=</
    1.11
     disintegration
    1.09
    了他
    1.09
     помещении
    1.09
     Tm
    1.05
    Activations Density 0.001%

    No Known Activations