© 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-16K
    7. 4834
    Prev
    Next
    INDEX
    Explanations

    able to, can tailor, to evolve

    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_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
    j
    1.21
     положения
    1.09
     Божи
    1.05
    v
    1.05
     порядке
    1.04
     možno
    1.03
     notwendig
    1.01
     actualmente
    1.00
     быть
    1.00
     dabei
    1.00
    POSITIVE LOGITS
    ти
    1.20
    المل
    1.16
    س
    1.15
    我也是
    1.09
    ின்
    1.02
    মা
    0.98
     isometry
    0.98
    0.98
    Გ
    0.96
    سلم
    0.95
    Activations Density 0.294%

    No Known Activations