© 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. 10-GEMMASCOPE-RES-131K
    7. 75565
    Prev
    Next
    INDEX
    Explanations

    camera, mobile, digital, archive, policy, Kellogg, Camel, text

    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_10/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
    もありますが
    -1.70
     they
    -1.44
     are
    -1.41
     경우
    -1.41
    जब
    -1.35
    大家都
    -1.34
     CULTURAL
    -1.34
     dacă
    -1.30
    ícias
    -1.29
    anging
    -1.27
    POSITIVE LOGITS
     and
    2.05
     "
    1.66
     which
    1.48
     liknande
    1.45
    voer
    1.40
     ONLY
    1.35
     where
    1.34
     Ľ
    1.34
     pomocou
    1.33
     on
    1.32
    Activations Density 0.196%

    No Known Activations