© 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. 84769
    Prev
    Next
    INDEX
    Explanations

    hashtag and explanation

    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
     current
    0.44
     caption
    0.43
     nCurrent
    0.42
    file
    0.42
    ﺎ
    0.40
     newspaper
    0.40
     name
    0.40
    !"));
    0.39
    なっている
    0.39
    班
    0.39
    POSITIVE LOGITS
     smoothies
    0.54
    മൂഹ
    0.51
    harmed
    0.48
     fleets
    0.48
     daimyo
    0.46
    سٹم
    0.46
     ermöglicht
    0.45
    ソニック
    0.45
     pohyb
    0.45
     klimat
    0.45
    Activations Density 0.007%

    No Known Activations