© 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. 181111
    Prev
    Next
    INDEX
    Explanations

    limited, reserve, stress, that

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

    explains origin, scheduled, shutdown

    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
    竅
    0.51
    夏
    0.48
    𝐭
    0.48
    畢
    0.48
    丹
    0.46
    фт
    0.46
    覺
    0.45
    沁
    0.44
    視頻
    0.43
    ફ
    0.43
    POSITIVE LOGITS
     XXI
    0.54
    onChange
    0.51
    ühm
    0.50
    urname
    0.48
    SignedIn
    0.48
    ondo
    0.46
    operateur
    0.46
     manufactures
    0.46
     Первая
    0.46
     XVII
    0.46
    Activations Density 0.000%

    No Known Activations