© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119846
    Prev
    Next
    INDEX
    Explanations

    permission or consent

    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
     said
    -1.84
     you
    -1.56
    衚
    -1.55
     sociedade
    -1.48
    を使った
    -1.41
     quoted
    -1.40
    憮
    -1.36
     refers
    -1.35
     didn
    -1.35
     are
    -1.35
    POSITIVE LOGITS
    4
    1.94
    8
    1.66
    3
    1.59
    7
    1.48
    6
    1.45
    9
    1.44
    5
    1.43
    richtet
    1.33
    0
    1.31
    griffen
    1.26
    Activations Density 0.025%

    No Known Activations