© 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. 25175
    Prev
    Next
    INDEX
    Explanations

    no shortage of

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

    meaning "or"

    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
     כי
    0.46
    鏢
    0.38
     দিলে
    0.38
    认为是
    0.38
     perché
    0.37
     può
    0.37
     Perché
    0.36
    粋
    0.36
     because
    0.35
     କ
    0.35
    POSITIVE LOGITS
     अथवा
    0.49
    Plenty
    0.44
     Plenty
    0.42
     kolejne
    0.41
     sebanyak
    0.41
    これからも
    0.39
    Meh
    0.39
    இவ்வாறு
    0.39
     mengalami
    0.39
     aquesta
    0.38
    Activations Density 0.003%

    No Known Activations