© 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. 110664
    Prev
    Next
    INDEX
    Explanations

    Permission to modify software

    np_acts-logits-general · gemini-2.5-flash-lite

    software license text, particularly phrases granting permission to copy, modify, and distribute.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     and
    -2.45
     also
    -1.68
     يون
    -1.51
     that
    -1.51
     börja
    -1.36
     with
    -1.35
     يول
    -1.31
    饜
    -1.30
     about
    -1.27
     つの
    -1.27
    POSITIVE LOGITS
    इटम
    1.68
     boneka
    1.56
     rahasia
    1.55
    AutoModerator
    1.52
     WHICH
    1.52
     signifikan
    1.48
    CCESS
    1.45
    Inggris
    1.42
     mimpi
    1.34
     hoher
    1.33
    Activations Density 0.309%

    No Known Activations