© 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. 77513
    Prev
    Next
    INDEX
    Explanations

    of

    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
     previewBuilder
    0.51
    魟
    0.47
    觧
    0.46
     своему
    0.43
     둘
    0.43
     wygl
    0.42
     соба
    0.41
    萵
    0.41
     মুহাম্মদ
    0.41
     пове
    0.40
    POSITIVE LOGITS
    ty
    0.54
    protect
    0.52
    so
    0.51
    t
    0.51
    ll
    0.50
    lr
    0.50
    i
    0.49
    b
    0.49
     with
    0.48
    casa
    0.48
    Activations Density 0.005%

    No Known Activations