© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24692
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    อยาก
    0.48
    บ่ง
    0.47
    либ
    0.47
     gosh
    0.46
    Abandon
    0.45
    🌰
    0.45
    ുകളുടെ
    0.44
    θέ
    0.43
    nomina
    0.43
    soluble
    0.43
    POSITIVE LOGITS
     N
    0.53
     Dose
    0.47
    صاف
    0.46
     Ei
    0.45
     Cost
    0.45
     Enem
    0.45
     E
    0.44
     ei
    0.44
     Merchandise
    0.44
     ई
    0.43
    Activations Density 0.001%

    No Known Activations