© 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. 13656
    Prev
    Next
    INDEX
    Explanations

    comfort settings

    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
     invece
    -1.25
    août
    -1.09
     réserv
    -1.09
    鳅
    -1.09
    riteria
    -1.08
    lamento
    -1.05
    paralleled
    -1.01
     ніж
    -0.99
    vello
    -0.99
     czarna
    -0.99
    POSITIVE LOGITS
     ὅ
    0.97
     innoc
    0.93
     ἄ
    0.88
     {$\
    0.88
     injus
    0.88
    '];
    0.88
    schod
    0.85
    én
    0.85
    Sziasztok
    0.84
     slightly
    0.84
    Activations Density 0.066%

    No Known Activations