© 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. 249164
    Prev
    Next
    INDEX
    Explanations

    creative ideas, highest quality

    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
     dna
    0.49
     Mojo
    0.49
     don
    0.48
     Dc
    0.48
     z
    0.47
     Finest
    0.46
     vast
    0.46
     vaste
    0.46
    a
    0.45
     Nm
    0.45
    POSITIVE LOGITS
    墻
    0.57
    積極的に
    0.55
    ตรฐาน
    0.52
    ξε
    0.52
    投资者
    0.50
    歐洲
    0.50
    मुख
    0.48
    ロ
    0.48
    バス
    0.48
    บ
    0.48
    Activations Density 0.001%

    No Known Activations