© 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. 27423
    Prev
    Next
    INDEX
    Explanations

    title for guides

    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
    wirken
    0.41
    0.41
    <0xE3>
    0.40
    ri
    0.40
    ্নি
    0.40
    עים
    0.40
    ni
    0.39
    frag
    0.37
    নিবার
    0.37
     erforderlich
    0.36
    POSITIVE LOGITS
     to
    0.64
     bagaimana
    0.52
     slic
    0.49
    стю
    0.47
    ដើម្បី
    0.47
     recuperação
    0.46
     untuk
    0.46
    𝚋
    0.46
    to
    0.45
    نسب
    0.45
    Activations Density 0.001%

    No Known Activations