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. 100557
    Prev
    Next
    INDEX
    Explanations

    describing mathematical or practical concepts

    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
    稔
    0.49
     faci
    0.48
     agréable
    0.46
    それぞれ
    0.45
    応援
    0.44
    t
    0.44
    LOTRE
    0.44
    㕸
    0.43
     ờ
    0.43
    ोत्
    0.41
    POSITIVE LOGITS
    -
    0.55
     marshmallow
    0.48
    —
    0.47
    リー
    0.46
     Realtor
    0.46
     slowdown
    0.45
     Realtors
    0.45
     byť
    0.43
     sturdy
    0.43
     galvanized
    0.43
    Activations Density 0.004%

    No Known Activations