© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 5234
    Prev
    Next
    INDEX
    Explanations

    slave, cut, mean, slowed, green

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     housework
    0.82
    房子
    0.70
     misfortunes
    0.66
    <unused675>
    0.65
    لاميذ
    0.64
    이는
    0.63
    旕
    0.61
    어요
    0.61
    하지
    0.61
    🤧
    0.60
    POSITIVE LOGITS
    /
    0.79
    そして
    0.76
     S
    0.73
     һәм
    0.73
     &
    0.73
     oraz
    0.72
     és
    0.65
     altamente
    0.64
     serta
    0.63
    および
    0.63
    Activations Density 0.000%

    No Known Activations