© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 99784
    Prev
    Next
    INDEX
    Explanations

    focus on past or present

    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_40_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
     Stud
    0.46
     creciendo
    0.45
    ôm
    0.40
     trabaj
    0.38
    壮
    0.37
    welcome
    0.37
    לא
    0.36
    विस
    0.36
    kath
    0.36
    rá
    0.36
    POSITIVE LOGITS
    。"
    0.44
    ।"
    0.41
    renewable
    0.41
    "।
    0.40
     renewable
    0.39
     Renewable
    0.39
    ಂಧ
    0.39
     =",
    0.39
    電動
    0.38
     (=
    0.38
    Activations Density 0.000%

    No Known Activations