© 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. 45415
    Prev
    Next
    INDEX
    Explanations

    actions, states, or goals

    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
     evas
    0.46
     य
    0.44
     ර
    0.43
     truth
    0.42
     y
    0.42
     heen
    0.42
     complement
    0.42
     gode
    0.41
     ray
    0.41
    ussa
    0.40
    POSITIVE LOGITS
    тивной
    0.46
    しみ
    0.46
     tatu
    0.44
    тивным
    0.44
    𝔞
    0.44
    чить
    0.44
     buku
    0.44
    ेडकर
    0.43
    лли
    0.43
    Comparing
    0.43
    Activations Density 0.000%

    No Known Activations