© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 139764
    Prev
    Next
    INDEX
    Explanations

    ID CARD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    is
    0.68
    leşt
    0.54
     گ
    0.50
     بیمار
    0.50
    <0x8F>
    0.50
    isierung
    0.49
     கீழ்
    0.48
    isierte
    0.48
    ીએ
    0.48
     şu
    0.47
    POSITIVE LOGITS
     солнца
    0.60
     Candles
    0.57
    ItemSelected
    0.56
    ।
    0.54
    Mother
    0.54
    CD
    0.52
    Girl
    0.52
    屜
    0.52
     thrones
    0.51
    し
    0.51
    Activations Density 0.001%

    No Known Activations