© 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. 12-GEMMASCOPE-2-RES-262K
    7. 11430
    Prev
    Next
    INDEX
    Explanations

    times of day (AM/PM/midnight)

    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_12_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
    is
    1.58
    u
    1.40
    er
    1.22
    aar
    1.20
    c
    1.16
    ata
    1.14
    ol
    1.13
    alion
    1.13
    ić
    1.10
    are
    1.08
    POSITIVE LOGITS
    Night
    1.31
    夜
    1.31
     nocturnal
    1.30
     الليل
    1.28
    ナイト
    1.24
     Night
    1.20
    रात्रि
    1.17
    nacht
    1.13
     रात
    1.09
    night
    1.08
    Activations Density 0.033%

    No Known Activations