© 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. 173330
    Prev
    Next
    INDEX
    Explanations

    quantities after specific words

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

    cultural and social information

    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
     menghubungi
    0.49
    鍘
    0.48
     जिसमे
    0.47
    圻
    0.47
    म्मीद
    0.46
     patching
    0.45
    বিবি
    0.45
    ကြောင်း
    0.44
     tasmim
    0.44
    螫
    0.44
    POSITIVE LOGITS
    …
    0.52
    …?
    0.50
     “‘
    0.48
    ────────
    0.45
    ugo
    0.45
    Cable
    0.44
     …
    0.43
     lump
    0.42
     rightly
    0.41
    は大
    0.41
    Activations Density 0.003%

    No Known Activations