© 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. 136393
    Prev
    Next
    INDEX
    Explanations

    https:// or brands

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

    means that python errors

    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
     collège
    0.47
    nce
    0.46
    and
    0.45
     and
    0.44
    m
    0.44
    nment
    0.43
    zhong
    0.42
    idar
    0.42
    école
    0.41
     school
    0.41
    POSITIVE LOGITS
     클릭
    0.49
    セレ
    0.48
     overflows
    0.45
    را
    0.45
    薙
    0.45
    ษฐ
    0.44
    ခ
    0.44
     бет
    0.44
     길이가
    0.43
     pagination
    0.42
    Activations Density 0.000%

    No Known Activations