© 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. 73750
    Prev
    Next
    INDEX
    Explanations

    financial or personal status

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

    unlikely pair or companions

    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
    Reg
    0.53
    second
    0.52
    G
    0.52
    priced
    0.51
    R
    0.49
    CEPT
    0.47
    Durch
    0.47
    instance
    0.46
    ro
    0.46
    grande
    0.46
    POSITIVE LOGITS
    擀
    0.54
    යන්
    0.52
     ⚫
    0.52
     冖
    0.52
    මාණ
    0.52
     ස
    0.50
     तैया
    0.50
     fxg
    0.50
    🥘
    0.49
     Spiral
    0.48
    Activations Density 0.000%

    No Known Activations