© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195539
    Prev
    Next
    INDEX
    Explanations

    training on Program services

    np_acts-logits-general · gemini-2.5-flash-lite

    programming and diverse subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purple
    0.45
     crying
    0.45
    ￥
    0.44
     whining
    0.44
     clerg
    0.44
     ग्रोथ
    0.43
     wine
    0.42
     ሲ
    0.42
     Hurts
    0.42
     मार्केट
    0.41
    POSITIVE LOGITS
     académica
    0.51
     উদ্বাস্তু
    0.49
     organizacional
    0.48
     preparada
    0.47
    ถมศึกษา
    0.47
    ässä
    0.46
    縝
    0.46
    faculty
    0.46
    égi
    0.45
    ଚ
    0.45
    Activations Density 0.001%

    No Known Activations