© 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. 224377
    Prev
    Next
    INDEX
    Explanations

    guys again, able to

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

    contribute, participate, observe

    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
     aktive
    0.47
     推
    0.46
     exhale
    0.46
     hongkong
    0.45
     hoch
    0.45
     enqueue
    0.45
    orh
    0.45
    ច្រើន
    0.45
     തിര
    0.44
     miss
    0.44
    POSITIVE LOGITS
    ৬
    0.51
    티
    0.51
    鹛
    0.50
    ྒྱ
    0.49
    лд
    0.48
    دى
    0.48
    狨
    0.46
    aunque
    0.45
    姒
    0.45
    મ
    0.44
    Activations Density 0.000%

    No Known Activations