© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 9837
    Prev
    Next
    INDEX
    Explanations

    signatures, color, number, music

    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_16k_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
    Fullscreen
    0.54
     якобы
    0.47
     вместо
    0.45
    निक
    0.43
     нужен
    0.42
    Feature
    0.42
     ужа
    0.42
     ፓ
    0.42
     yacht
    0.42
     автомоби
    0.41
    POSITIVE LOGITS
    zed
    0.40
    erequisites
    0.40
     injured
    0.38
     Orchard
    0.38
     clippings
    0.38
    med
    0.37
    िल्या
    0.37
    سمى
    0.37
    ised
    0.37
    ahorse
    0.37
    Activations Density 0.075%

    No Known Activations