© 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. 25215
    Prev
    Next
    INDEX
    Explanations

    understanding the

    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
    ol
    0.52
    m
    0.48
     Password
    0.46
    um
    0.46
     Geol
    0.46
    тово
    0.46
    vin
    0.45
    t
    0.45
    av
    0.45
    vot
    0.45
    POSITIVE LOGITS
    اري
    0.47
    ุ่ม
    0.46
    زمة
    0.45
     диа
    0.44
    دي
    0.43
     dinâmica
    0.42
     restlessness
    0.41
    мати
    0.41
    کتر
    0.41
    ຈະ
    0.40
    Activations Density 0.001%

    No Known Activations