Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 85086
    Prev
    Next
    INDEX
    Explanations

    projects leading to new opportunities

    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
    گ
    0.52
    銠
    0.52
     নিরাপ
    0.51
    kanen
    0.50
    ام
    0.49
    ArchiveAction
    0.49
    嵓
    0.49
     прадстаў
    0.48
     النرويج
    0.48
     द्
    0.48
    POSITIVE LOGITS
     cafe
    0.54
    /
    0.48
     Bast
    0.47
    de
    0.44
     Lord
    0.44
     /
    0.44
     threat
    0.43
    token
    0.43
     Abandon
    0.43
    res
    0.42
    Activations Density 0.006%

    No Known Activations