© 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. 27040
    Prev
    Next
    INDEX
    Explanations

    API functions, keys, and gate

    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
     crucifixion
    0.62
    ího
    0.60
     уви
    0.59
     suffoc
    0.59
     тан
    0.59
     мело
    0.59
    ală
    0.59
    ᑉ
    0.59
    <unused626>
    0.58
    <unused987>
    0.58
    POSITIVE LOGITS
    that
    0.97
    1
    0.96
    ك
    0.85
    2
    0.79
     a
    0.77
    c
    0.69
    ח
    0.68
    Changes
    0.68
    า
    0.67
    ן
    0.67
    Activations Density 0.041%

    No Known Activations