© 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-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1221
    Prev
    Next
    INDEX
    Explanations

    cracked, brackets, intrigue, gritty

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ్య
    0.89
    ــــ
    0.79
    otron
    0.78
     공
    0.76
     minu
    0.74
     subtle
    0.72
    etl
    0.72
     empty
    0.70
     대
    0.70
    ـــ
    0.68
    POSITIVE LOGITS
    acking
    1.33
    agedy
    1.19
    acked
    1.13
    agment
    1.08
    ashing
    1.08
    igg
    1.05
    ussels
    1.03
    igger
    1.03
    acket
    1.02
    incipal
    1.02
    Activations Density 0.407%

    No Known Activations