© 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. 177318
    Prev
    Next
    INDEX
    Explanations

    before, after, use

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

    before something else

    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
    Ə
    0.46
     eighth
    0.46
    MiddleLeft
    0.46
    यत्त
    0.46
     italian
    0.45
     mythology
    0.45
    ູ່
    0.44
     hazy
    0.44
     Mythology
    0.44
    ເວລາ
    0.44
    POSITIVE LOGITS
    мов
    0.46
    dataset
    0.46
     länge
    0.45
    пуск
    0.45
    ];
    0.44
    [/
    0.43
     রোহিঙ্গ
    0.43
    crs
    0.43
    achable
    0.42
     dienen
    0.42
    Activations Density 0.003%

    No Known Activations