© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3820
    Prev
    Next
    INDEX
    Explanations

    automatic, remote, or direct operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     because
    0.82
     BECAUSE
    0.79
     EXPECT
    0.72
     initial
    0.71
    –
    0.69
     brand
    0.67
     expect
    0.67
    !
    0.66
    —
    0.65
     –
    0.65
    POSITIVE LOGITS
     remotely
    1.60
     asynchronously
    1.49
     secara
    1.43
     wirelessly
    1.40
     automaticamente
    1.27
     dynamically
    1.25
     באופן
    1.21
     manualmente
    1.19
    Automatically
    1.19
     Secara
    1.18
    Activations Density 0.437%

    No Known Activations