© 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. 76710
    Prev
    Next
    INDEX
    Explanations

    for those, every occasion, money onto

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

    specific framework

    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
     anillo
    0.59
     scholarly
    0.52
     sympathize
    0.47
     buckle
    0.47
     haem
    0.46
    욌
    0.46
     hemolysis
    0.46
     scholarship
    0.45
     hospitalization
    0.45
     thalassemia
    0.44
    POSITIVE LOGITS
    Batt
    0.48
    ASI
    0.46
    ]:
    0.46
    ].
    0.45
    linkColor
    0.45
    tissue
    0.45
    2
    0.44
    8
    0.44
    ],
    0.44
    IPC
    0.44
    Activations Density 0.000%

    No Known Activations