© 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. 89312
    Prev
    Next
    INDEX
    Explanations

    cases , upon , supported by , Wales

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

    depending on

    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
     practica
    0.46
     Rin
    0.45
    暗
    0.45
     Deve
    0.45
     Joh
    0.45
     controle
    0.44
     controla
    0.44
     manchas
    0.43
    上げ
    0.43
    EXPERIMENTAL
    0.43
    POSITIVE LOGITS
    ApiKey
    0.47
    📨
    0.46
     వచ్చే
    0.42
    🕔
    0.41
    ご確認
    0.41
     disponibilités
    0.41
     authToken
    0.40
    🕒
    0.40
    对应的
    0.40
    న్స్
    0.40
    Activations Density 0.006%

    No Known Activations