© 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. 15-GEMMASCOPE-2-RES-262K
    7. 70107
    Prev
    Next
    INDEX
    Explanations

    will do

    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_15_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
     runde
    1.76
     settim
    1.72
    迸
    1.70
    aupt
    1.65
    arbeitet
    1.61
    rhein
    1.58
    iseite
    1.57
     Lạt
    1.55
    TimeTo
    1.55
     ہتھیار
    1.53
    POSITIVE LOGITS
    image
    1.59
    prev
    1.52
    pre
    1.50
    ena
    1.47
    z
    1.43
    ex
    1.41
    help
    1.41
    English
    1.40
    Pre
    1.40
    en
    1.40
    Activations Density 0.000%

    No Known Activations