© 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. 24692
    Prev
    Next
    INDEX
    Explanations

    way to

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

    thoroughness, resulted

    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
     gosh
    0.50
    บ่ง
    0.47
    🌰
    0.47
    อยาก
    0.47
    ]]))
    0.46
    ുകളുടെ
    0.44
    soluble
    0.43
    떴
    0.43
    Biden
    0.42
    θέ
    0.42
    POSITIVE LOGITS
     Dose
    0.52
     N
    0.52
     Ei
    0.50
     ei
    0.50
     ई
    0.49
    صاف
    0.49
     EI
    0.49
    WERS
    0.48
     Ə
    0.47
     E
    0.46
    Activations Density 0.000%

    No Known Activations