© 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. 17-GEMMASCOPE-2-RES-16K
    7. 12042
    Prev
    Next
    INDEX
    Explanations

    rotation, twist, tilt, crank

    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_17_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
    ложение
    1.25
     Distinct
    1.19
    ⇣
    1.16
    щин
    1.15
    ↝
    1.15
    ađ
    1.14
    лизи
    1.13
    ются
    1.13
     distinct
    1.12
    verifica
    1.11
    POSITIVE LOGITS
     poverty
    1.15
     Recreation
    1.05
    z
    1.01
     Trader
    0.99
     Pendidikan
    0.98
     Borrower
    0.98
     δεύτε
    0.98
     eyebrows
    0.98
    pK
    0.97
     ngược
    0.97
    Activations Density 0.001%

    No Known Activations