© 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. 36100
    Prev
    Next
    INDEX
    Explanations

    checking for existence of attributes/keys

    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
    osome
    -1.02
     для
    -0.96
     was
    -0.92
    や
    -0.91
    หรือ
    -0.90
     Faktoren
    -0.90
     ワゴン
    -0.90
     Dinas
    -0.90
     είναι
    -0.89
     praticamente
    -0.89
    POSITIVE LOGITS
     suficientes
    1.23
     then
    1.12
    ところに
    1.08
     entonces
    1.05
     никаких
    1.04
    тири
    1.02
     dessen
    1.00
    </h2>
    0.99
     técnicos
    0.99
     snack
    0.99
    Activations Density 0.004%

    No Known Activations