© 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. 40606
    Prev
    Next
    INDEX
    Explanations

    letters T and t

    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
    ar
    1.26
    ing
    1.25
    ان
    1.25
    る
    1.24
    a
    1.21
    as
    1.19
    ة
    1.18
    ા
    1.16
    ib
    1.15
    at
    1.11
    POSITIVE LOGITS
    habitants
    1.40
     codons
    1.34
     worded
    1.33
     gramos
    1.32
    تن
    1.31
    旛
    1.30
    𝙡
    1.30
    miktar
    1.29
     uczni
    1.27
    𝙠
    1.26
    Activations Density 0.000%

    No Known Activations