© 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. 80356
    Prev
    Next
    INDEX
    Explanations

    common word sequence pairings

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

    SSMS Locust Safety

    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
     Haag
    0.51
     Vorte
    0.46
    これが
    0.45
    این
    0.45
    歴
    0.44
    บร
    0.44
     Leverkusen
    0.43
     tini
    0.42
     Comput
    0.42
    কার্য
    0.41
    POSITIVE LOGITS
     மேற்கொள்ள
    0.45
    keeping
    0.44
     Thumb
    0.44
    ័រ
    0.44
    ﯼ
    0.43
    男孩
    0.43
     ermöglichen
    0.42
     কাশ্ম
    0.42
    Idx
    0.42
     रखी
    0.42
    Activations Density 0.000%

    No Known Activations