© 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. 100296
    Prev
    Next
    INDEX
    Explanations

    `fundamental` or `powerful`

    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
    事
    0.47
    RP
    0.46
    渡
    0.44
    ्राष्ट
    0.43
     REST
    0.43
    ნი
    0.43
    REST
    0.43
    理
    0.42
    ПО
    0.42
    湇
    0.42
    POSITIVE LOGITS
    ké
    0.53
     caule
    0.52
     sirop
    0.49
     щ
    0.47
    úncia
    0.47
     Hinweis
    0.46
     स्तंभ
    0.46
    ůli
    0.46
     صاف
    0.45
     popsicle
    0.45
    Activations Density 0.001%

    No Known Activations