© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1557
    Prev
    Next
    INDEX
    Explanations

    moving beyond innovation and efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    will
    0.58
    esteem
    0.58
     नक्की
    0.56
     Seeing
    0.53
     Hearing
    0.53
     नारेबाजी
    0.50
     paraît
    0.50
    _
    0.49
     (~
    0.49
    sentence
    0.49
    POSITIVE LOGITS
     효율
    1.31
     innovating
    1.20
     innovative
    1.19
     effiz
    1.11
     иннова
    1.10
     innovate
    1.07
     efficient
    1.05
     эффектив
    1.04
     선보
    1.03
     편리
    1.02
    Activations Density 0.024%

    No Known Activations