© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123011
    Prev
    Next
    INDEX
    Explanations

    selling products or activities

    np_acts-logits-general · gemini-2.5-flash-lite

    science behind, drones crash, berries, seeds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    firstChild
    0.42
    ئیں
    0.40
    playable
    0.39
    تی
    0.39
    بال
    0.39
    琶
    0.39
    clickHandler
    0.38
     بنائیں
    0.38
     уви
    0.38
    র
    0.37
    POSITIVE LOGITS
    inh
    0.50
     đông
    0.50
    ❛
    0.49
    auté
    0.47
     পরিষেবা
    0.47
    が通販
    0.45
    ola
    0.45
     diversión
    0.45
     tales
    0.44
    ône
    0.44
    Activations Density 0.001%

    No Known Activations