© 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-65K
    7. 49259
    Prev
    Next
    INDEX
    Explanations

    right shift

    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_65k_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
    је
    0.55
    abı
    0.52
    нк
    0.52
    ciąż
    0.51
    uje
    0.50
     존재하는
    0.50
    buje
    0.46
    ק
    0.46
    ik
    0.46
    cache
    0.46
    POSITIVE LOGITS
     ventilation
    0.52
     slotted
    0.48
     Ventilation
    0.47
     shipyard
    0.46
     dichloromethane
    0.43
     by
    0.42
     ferries
    0.42
     Marshall
    0.41
     logical
    0.41
     milk
    0.40
    Activations Density 0.001%

    No Known Activations