© 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. 163868
    Prev
    Next
    INDEX
    Explanations

    phrases like "out of", "advantage of", "world of"

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

    may require more

    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
    帰
    0.45
     equaling
    0.44
    事を
    0.43
    AndTime
    0.43
    ラル
    0.42
    鐵
    0.42
    টাকে
    0.41
    rite
    0.41
     étroites
    0.40
    affection
    0.40
    POSITIVE LOGITS
    TANK
    0.48
    ньше
    0.46
    мм
    0.46
    განი
    0.46
    urangi
    0.45
    는
    0.44
     SOP
    0.44
    :
    0.44
    하시
    0.44
     установка
    0.44
    Activations Density 0.001%

    No Known Activations