© 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. 70854
    Prev
    Next
    INDEX
    Explanations

    sequential messages

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

    reporting negative conditions or specific items

    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
    qh
    0.53
     oti
    0.48
    q
    0.47
    zę
    0.44
     gj
    0.43
     gpu
    0.43
    weł
    0.43
    駄
    0.43
    Cyber
    0.43
    т
    0.42
    POSITIVE LOGITS
     последова
    0.42
    潜
    0.42
    <unused24>
    0.41
     successivement
    0.39
    潛
    0.39
     পৌঁছ
    0.39
     communiqué
    0.38
     संदेश
    0.38
     comunicado
    0.38
     دنبال
    0.38
    Activations Density 0.000%

    No Known Activations