© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8935
    Prev
    Next
    INDEX
    Explanations

    morning/afternoon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    时间和
    0.71
     Перейти
    0.70
     mutta
    0.70
     Unless
    0.69
     takže
    0.65
     If
    0.63
     Anyone
    0.62
     -"
    0.62
    ﺑ
    0.61
     Anything
    0.61
    POSITIVE LOGITS
    /
    4.22
    -/
    2.39
    ／
    2.38
    /(
    2.20
    ()/
    2.17
     /
    2.08
     bzw
    2.05
    หรือ
    1.96
    ∕
    1.89
    /_
    1.88
    Activations Density 0.003%

    No Known Activations