© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1559
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     organisers
    2.53
     historians
    2.30
    ,:
    2.30
     schedules
    2.27
     (’
    2.26
     methods
    2.23
     schemes
    2.23
     arranges
    2.16
     supplemented
    2.15
    astic
    2.14
    POSITIVE LOGITS
    7
    3.04
    6
    2.80
    8
    2.73
    3
    2.70
    4
    2.64
    5
    2.61
    9
    2.53
    ۷
    2.41
     базо
    2.33
    قل
    2.29
    Activations Density 1.486%

    No Known Activations