© 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. 1054
    Prev
    Next
    INDEX
    Explanations

    by your means

    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
    я
    0.95
     pokud
    0.93
     dealt
    0.88
     ketika
    0.87
     dacă
    0.86
    mpg
    0.85
     Selain
    0.85
    afety
    0.84
    ১
    0.82
    ここは
    0.82
    POSITIVE LOGITS
     virtue
    2.92
     means
    2.70
     dint
    2.43
    means
    2.26
     way
    2.20
    zantine
    2.10
     MEANS
    2.07
    Means
    1.95
     Means
    1.93
     analogy
    1.87
    Activations Density 0.433%

    No Known Activations