© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 10548
    Prev
    Next
    INDEX
    Explanations

    planning future actions

    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
    Negative Logits
    tering
    1.13
     архи
    1.08
    ters
    1.07
     Critique
    1.06
     мүмк
    1.05
    ibald
    1.02
    ü
    0.98
     וא
    0.96
    garten
    0.96
     書
    0.96
    POSITIVE LOGITS
    お
    1.42
    id
    1.35
    a
    1.18
    お金
    1.17
    いました
    1.16
    enjoy
    1.13
    L
    1.13
    おしゃれ
    1.11
    s
    1.11
    '
    1.11
    Activations Density 0.159%

    No Known Activations