© 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. 40518
    Prev
    Next
    INDEX
    Explanations

    took with time or action

    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
    y
    1.84
    in
    1.69
    p
    1.32
    is
    1.29
    a
    1.21
    r
    1.21
    w
    1.20
    1.19
    Password
    1.16
    Code
    1.10
    POSITIVE LOGITS
    3
    1.55
    다
    1.34
    你
    1.34
    க்
    1.30
    いません
    1.30
    もちろん
    1.23
    ปี
    1.20
    いを
    1.17
    м
    1.17
     społec
    1.16
    Activations Density 0.004%

    No Known Activations