© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1513
    Prev
    Next
    INDEX
    Explanations

    despite challenges

    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
     (
    1.81
     (!
    1.77
     (!)
    1.71
     (=
    1.70
     (&
    1.59
    (!)
    1.58
    (!
    1.55
    !
    1.53
     ([
    1.53
     ('
    1.52
    POSITIVE LOGITS
     meski
    1.41
     amid
    1.35
     pihaknya
    1.33
     ahead
    1.29
    following
    1.23
    Following
    1.20
    ahead
    1.19
    Ahead
    1.19
    despite
    1.16
     pese
    1.15
    Activations Density 0.252%

    No Known Activations