© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91865
    Prev
    Next
    INDEX
    Explanations

    colors and their combinations

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

    green color definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     факт
    0.45
     conforto
    0.44
    Officers
    0.43
     ఇటీ
    0.42
    Fare
    0.42
    ឿង
    0.42
    醫
    0.42
    Investors
    0.42
    Interview
    0.41
    Fact
    0.41
    POSITIVE LOGITS
     green
    0.50
     緑
    0.50
     violet
    0.47
     سبز
    0.47
     Grün
    0.47
     グリーン
    0.46
     зелены
    0.46
     pastel
    0.45
     piezoelectric
    0.45
     grü
    0.45
    Activations Density 0.023%

    No Known Activations