© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36161
    Prev
    Next
    INDEX
    Explanations

    intent goal representation

    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
    ned
    0.44
     پ
    0.42
    umni
    0.42
    t
    0.42
    прочем
    0.42
    徝
    0.41
    hart
    0.41
     screenshots
    0.40
    evším
    0.40
    }")
    0.40
    POSITIVE LOGITS
     nylon
    0.50
     kadın
    0.45
     kullanıcı
    0.44
     women
    0.44
     endl
    0.43
     miljoen
    0.43
     counterpart
    0.43
     engineers
    0.42
     spool
    0.42
     mał
    0.42
    Activations Density 0.004%

    No Known Activations