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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    referencing below

    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
     Иванович
    0.44
    Ij
    0.43
     Ij
    0.43
     Ontario
    0.43
     Igreja
    0.43
     Grove
    0.42
     Forms
    0.42
     |_
    0.42
    ologically
    0.41
    อากาศ
    0.41
    POSITIVE LOGITS
    ține
    0.53
    éf
    0.48
     purposely
    0.48
     willfully
    0.46
    lá
    0.45
     স্থাপন
    0.44
    珊
    0.44
    ັດ
    0.43
     reveal
    0.42
    lish
    0.41
    Activations Density 0.011%

    No Known Activations