© 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. 112837
    Prev
    Next
    INDEX
    Explanations

    calculating, notes, outcome, DM

    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
     tracks
    0.42
    ἷ
    0.40
    är
    0.39
    loaded
    0.39
    uries
    0.39
    迷
    0.38
    乾
    0.38
    QU
    0.37
    rik
    0.36
    id
    0.36
    POSITIVE LOGITS
     allons
    0.59
     选择
    0.57
    🖒
    0.57
     almacenamiento
    0.57
     О
    0.55
     intraven
    0.55
     Про
    0.55
     Algunas
    0.55
     consideramos
    0.55
     FreeBSD
    0.54
    Activations Density 0.001%

    No Known Activations