© 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. 53204
    Prev
    Next
    INDEX
    Explanations

    union leadership, coal gas, law removed

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

    saw a, bird mimics, Industry standards, computer system

    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
    wakilan
    0.48
    नमस्ते
    0.46
    朋友們
    0.45
     المؤمن
    0.45
    碐
    0.44
     Zusätzlich
    0.44
    侢
    0.44
     प्रेरणात्मक
    0.44
     направлении
    0.43
    轲
    0.43
    POSITIVE LOGITS
     gynec
    0.45
    /
    0.44
    |
    0.43
     trade
    0.42
     travelled
    0.42
     chlorine
    0.42
     or
    0.42
     name
    0.42
    /*
    0.41
     political
    0.41
    Activations Density 0.021%

    No Known Activations