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. 111384
    Prev
    Next
    INDEX
    Explanations

    source directory separator ether space

    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
     voitures
    0.57
    ೕ
    0.55
     recieved
    0.52
    све
    0.48
     obtuvo
    0.48
    TintMode
    0.46
     abducted
    0.46
    鲑
    0.46
    saved
    0.46
     wellknown
    0.45
    POSITIVE LOGITS
    inen
    0.52
    Ver
    0.45
    HD
    0.44
    Goal
    0.44
    Con
    0.44
    USB
    0.42
    Er
    0.42
    ด้าน
    0.41
    ANDO
    0.41
    LEY
    0.41
    Activations Density 0.010%

    No Known Activations