© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 883
    Prev
    Next
    INDEX
    Explanations

    pay out or thoughts of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ей
    0.54
     bén
    0.53
     sinusoidal
    0.53
     вто
    0.52
    些
    0.52
     ее
    0.52
     '".$
    0.52
     Mr
    0.52
    是我
    0.51
     ī
    0.51
    POSITIVE LOGITS
     PLUS
    0.82
    PLUS
    0.76
     plus
    0.74
     Together
    0.71
     minus
    0.69
     whilst
    0.69
     consequently
    0.68
     Consequently
    0.68
     therefore
    0.68
     aswell
    0.67
    Activations Density 0.775%

    No Known Activations