© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2906
    Prev
    Next
    INDEX
    Explanations

    setting the table

    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_34/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
    Newton
    -0.81
    ㅂ
    -0.81
     NR
    -0.81
    ctober
    -0.78
     network
    -0.78
    چگونه
    -0.71
     Network
    -0.71
     Newton
    -0.71
    __;
    -0.71
     Treas
    -0.70
    POSITIVE LOGITS
     setting
    2.67
     settings
    2.30
    Setting
    2.23
     Setting
    2.13
    setting
    2.03
    SETTING
    1.98
     table
    1.88
    设置
    1.85
     SETTING
    1.84
     setup
    1.76
    Activations Density 0.014%

    No Known Activations