© 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. 36091
    Prev
    Next
    INDEX
    Explanations

    unlocking cost savings and new systems

    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
     lesions
    0.47
     radiography
    0.47
    ферен
    0.46
     fondamentali
    0.46
    ⃣
    0.45
     separations
    0.45
     renormal
    0.45
     enzymes
    0.45
     fundamental
    0.45
     multiplications
    0.44
    POSITIVE LOGITS
    ut
    0.54
     Audio
    0.45
     Augmented
    0.42
    v
    0.42
     Usuario
    0.42
     Dialog
    0.41
    aj
    0.41
     Hot
    0.41
    ută
    0.41
     ग्रे
    0.40
    Activations Density 0.000%

    No Known Activations