© 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. 160200
    Prev
    Next
    INDEX
    Explanations

    High Line, sanctions against, unquestionably assist

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

    example, relates to

    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
    émor
    0.48
    geten
    0.46
    峽
    0.46
    減少
    0.46
    წიფ
    0.45
    سر
    0.45
    减少
    0.44
    前面的
    0.44
    tank
    0.44
    能不能
    0.43
    POSITIVE LOGITS
     Deviation
    0.49
     예배
    0.48
     یہودیوں
    0.46
     K
    0.46
     Rico
    0.45
     Latitude
    0.45
     outlier
    0.44
     Equation
    0.43
     coalgebra
    0.43
     Prejudice
    0.43
    Activations Density 0.001%

    No Known Activations