© 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. 25147
    Prev
    Next
    INDEX
    Explanations

    specific items followed by details

    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
     ओ
    0.50
    ごとに
    0.47
     развития
    0.46
    細胞
    0.45
    testen
    0.44
    かけ
    0.44
    問題
    0.43
     câte
    0.43
     cavern
    0.43
     prognosis
    0.42
    POSITIVE LOGITS
    ľad
    0.46
    ijdens
    0.45
    IFICATION
    0.44
    imsu
    0.44
    <0x95>
    0.43
    Ḩ
    0.41
    Ketika
    0.40
     moieties
    0.39
     equipments
    0.39
    isjon
    0.39
    Activations Density 0.001%

    No Known Activations