© 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. 104898
    Prev
    Next
    INDEX
    Explanations

    maintain, elasticity

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

    non-english phrases

    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
     апре
    0.45
    ];
    0.44
    Grand
    0.43
     чемпиона
    0.42
     tenacious
    0.42
     Вален
    0.42
    Gal
    0.42
     Clermont
    0.41
    いわ
    0.41
    ран
    0.41
    POSITIVE LOGITS
    ד
    0.57
    ס
    0.47
    elastic
    0.47
    㑓
    0.47
     Maintaining
    0.45
    খিক
    0.45
     elasticity
    0.45
     później
    0.45
     jumlah
    0.44
    籟
    0.44
    Activations Density 0.000%

    No Known Activations