© 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. 105107
    Prev
    Next
    INDEX
    Explanations

    du words

    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
    </strong>
    -3.02
    鬟
    -2.98
    ꜆
    -2.55
    </em>
    -2.53
     unſ
    -2.48
    Possibly
    -2.48
    眥
    -2.47
     sogen
    -2.44
    ⽥
    -2.34
    踅
    -2.33
    POSITIVE LOGITS
     While
    2.98
     We
    2.64
     was
    2.53
     After
    2.52
     Because
    2.50
     Despite
    2.50
     However
    2.42
     Although
    2.42
    \
    2.38
     Our
    2.31
    Activations Density 0.012%

    No Known Activations