© 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. 114797
    Prev
    Next
    INDEX
    Explanations

    conditional logic and programming structures

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

    APT groups targeting entities

    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
     Націона
    0.52
     ด้วย
    0.49
     เพื่อ
    0.48
     сприя
    0.46
    𝐊
    0.45
     Дан
    0.44
     ENGINEER
    0.44
     Ꭰ
    0.42
    —“
    0.42
     розташо
    0.42
    POSITIVE LOGITS
     swans
    0.45
    elif
    0.45
     varias
    0.44
    if
    0.44
    myTransform
    0.44
    ifel
    0.44
    其它
    0.42
    件事
    0.42
    ifelse
    0.42
    가지
    0.41
    Activations Density 0.001%

    No Known Activations