© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47463
    Prev
    Next
    INDEX
    Explanations

    colors ending in ish

    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
    रूप
    -0.79
     soooo
    -0.78
     sooo
    -0.77
    まっ
    -0.77
     PROCESSING
    -0.76
    ピュー
    -0.75
     loud
    -0.75
    </b>
    -0.74
     остальные
    -0.74
    大好き
    -0.74
    POSITIVE LOGITS
    brown
    1.43
    ish
    1.29
    grey
    1.21
     brown
    1.19
    gray
    1.16
    purple
    1.13
    Brown
    1.06
    ISH
    1.05
     gray
    1.02
     Brown
    1.00
    Activations Density 0.026%

    No Known Activations