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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 8379
    Prev
    Next
    INDEX
    Explanations

    daily plans or structure

    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
     siehe
    0.49
     THRO
    0.48
    receptor
    0.48
    রে
    0.45
     hinsichtlich
    0.45
     größ
    0.43
    Y
    0.43
    ير
    0.42
     cilind
    0.41
    শ
    0.41
    POSITIVE LOGITS
     Daily
    0.59
    ur
    0.52
    Daily
    0.47
    wn
    0.45
    cuna
    0.43
     Labour
    0.43
     Accuracy
    0.43
     엄청
    0.42
     Construct
    0.42
     Maths
    0.41
    Activations Density 0.000%

    No Known Activations