© 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. 94228
    Prev
    Next
    INDEX
    Explanations

    tech and AI discussions

    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
    ത്തിനായി
    0.52
     刺繍
    0.50
     для
    0.49
    Suit
    0.49
    𝒚
    0.48
    прода
    0.48
     прода
    0.47
     впечат
    0.47
     Suit
    0.46
    പാടി
    0.46
    POSITIVE LOGITS
     provider
    0.43
    픕
    0.42
    riere
    0.41
     stát
    0.40
     providers
    0.39
     barometer
    0.39
     contraception
    0.39
     journaling
    0.38
    ucine
    0.38
    建物
    0.38
    Activations Density 0.004%

    No Known Activations