© 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. 148599
    Prev
    Next
    INDEX
    Explanations

    information, device, or listing

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

    plans and fees

    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
     결정
    0.46
    ствием
    0.46
    ூழ
    0.46
    ᱗
    0.45
     компенса
    0.45
     justifyContent
    0.43
     প্রথমেই
    0.43
    성과
    0.43
     결과
    0.43
    彠
    0.43
    POSITIVE LOGITS
    n
    0.53
    t
    0.49
    cau
    0.48
    cle
    0.46
    c
    0.46
    k
    0.46
     KLE
    0.43
    Xbox
    0.43
    coc
    0.43
    kter
    0.43
    Activations Density 0.001%

    No Known Activations