© 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. 40450
    Prev
    Next
    INDEX
    Explanations

    training details transparently available

    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
     Solids
    0.47
    ي
    0.46
    TL
    0.46
    äure
    0.46
    </sub>
    0.45
    RF
    0.45
    W
    0.45
    一种
    0.44
     Inorganic
    0.44
    ა
    0.44
    POSITIVE LOGITS
    身長
    0.47
     brindar
    0.45
     brinda
    0.44
     assistance
    0.43
     viktig
    0.43
     करीब
    0.43
     respective
    0.42
    རྒྱ
    0.42
    費用
    0.42
    心情
    0.42
    Activations Density 0.004%

    No Known Activations