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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 694
    Prev
    Next
    INDEX
    Explanations

    early stages of fields

    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
    ट
    1.56
    ला
    1.45
    ל
    1.41
    িন
    1.38
    '
    1.34
    ’
    1.21
    িল
    1.20
    াস
    1.20
    li
    1.19
    ד
    1.16
    POSITIVE LOGITS
    h
    1.23
     في
    1.13
    ání
    1.13
    𝐧
    1.13
    с
    1.12
    𝐠
    1.10
    0
    1.09
    𝐞
    1.06
    禀
    1.06
    颇
    1.05
    Activations Density 0.038%

    No Known Activations