© 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. 670
    Prev
    Next
    INDEX
    Explanations

    repetitive actions or words

    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
     분류
    0.87
     freelancer
    0.79
     phishing
    0.78
     hitbox
    0.73
    📈
    0.72
     заинтере
    0.72
     disequ
    0.72
    ylmethyl
    0.71
    👽
    0.71
     persondata
    0.71
    POSITIVE LOGITS
     prayers
    2.80
     prayer
    2.65
     ritual
    2.65
     Prayers
    2.63
     rituals
    2.59
     ceremony
    2.57
     ceremonies
    2.56
     Prayer
    2.46
     praying
    2.45
     rites
    2.35
    Activations Density 1.393%

    No Known Activations