© 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. 56895
    Prev
    Next
    INDEX
    Explanations

    starting and finishing tasks

    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
     ['(?
    0.50
    選び
    0.46
    畩
    0.46
    overrightarrow
    0.45
     सुनेंरोक
    0.45
    เมริกา
    0.45
     favoriser
    0.44
    లేదు
    0.43
    λεκ
    0.43
    尼亚
    0.43
    POSITIVE LOGITS
     after
    0.51
    after
    0.49
     a
    0.47
     during
    0.46
     once
    0.45
    '
    0.44
     somewhere
    0.44
    during
    0.43
     Once
    0.43
     found
    0.43
    Activations Density 0.002%

    No Known Activations