© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1803
    Prev
    Next
    INDEX
    Explanations

    loading state

    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_16_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
    ओं
    0.85
     are
    0.79
    ः
    0.76
    கள்
    0.73
    いますが
    0.70
    یث
    0.70
    اعری
    0.69
     نہایت
    0.68
    ۔
    0.68
    .’
    0.68
    POSITIVE LOGITS
    is
    1.47
    n
    1.20
    a
    1.16
    an
    1.13
    ه
    1.09
    هي
    1.09
    ة
    1.05
    ن
    1.04
    ת
    1.02
    ان
    1.01
    Activations Density 0.010%

    No Known Activations