© 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. 216941
    Prev
    Next
    INDEX
    Explanations

    calibration and details

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

    explains complex or huge topics

    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
    豆腐
    0.51
    好み
    0.48
    ти
    0.48
    stimulation
    0.48
    normalization
    0.46
    ે
    0.45
     सरकार
    0.44
    helium
    0.42
    empire
    0.42
    комо
    0.42
    POSITIVE LOGITS
     whereby
    0.50
    仴
    0.46
     Seda
    0.46
    zględ
    0.44
     Omer
    0.43
     espèce
    0.43
     surmounted
    0.43
    తో
    0.42
    قات
    0.42
     waarmee
    0.42
    Activations Density 0.002%

    No Known Activations