© 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. 40-GEMMASCOPE-2-RES-262K
    7. 9625
    Prev
    Next
    INDEX
    Explanations

    adjective descriptions and their derived forms

    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_40_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
     jumlah
    0.29
     TOE
    0.29
     hồn
    0.27
     zarówno
    0.26
     zowel
    0.26
     乀
    0.26
    ALWAYS
    0.25
     }}">
    0.25
    ဝ်
    0.25
    ક્ટર
    0.25
    POSITIVE LOGITS
    est
    0.60
    ening
    0.52
    ened
    0.50
    ness
    0.48
    ies
    0.47
    ish
    0.43
    hearted
    0.43
    ie
    0.40
    nesses
    0.39
    comings
    0.39
    Activations Density 0.092%

    No Known Activations