© 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. 67772
    Prev
    Next
    INDEX
    Explanations

    approval of lease

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

    making food and code

    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
    j
    0.55
    )
    0.53
    g
    0.51
    ang
    0.51
    г
    0.49
    ג
    0.48
    ong
    0.48
    jal
    0.46
    \]
    0.46
    f
    0.46
    POSITIVE LOGITS
    ανο
    0.49
     creating
    0.48
     vytvá
    0.48
     ध्वस्त
    0.47
     편리
    0.47
     உருவாக்கி
    0.47
     étage
    0.46
     책임
    0.46
     criar
    0.45
    瀣
    0.45
    Activations Density 0.000%

    No Known Activations