© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 137303
    Prev
    Next
    INDEX
    Explanations

    crucial for AC signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     furl
    0.40
    শিংটন
    0.40
     معاش
    0.40
    ريب
    0.39
    %)$
    0.39
    senior
    0.38
    .___
    0.37
     formContext
    0.36
     ਯ
    0.35
    اعری
    0.35
    POSITIVE LOGITS
    <h3>
    0.44
     করলেন
    0.42
     વાંચો
    0.42
    トル
    0.39
     Фло
    0.37
    Element
    0.37
     Fluor
    0.37
     Venus
    0.37
     Hermes
    0.37
     Camus
    0.37
    Activations Density 0.000%

    No Known Activations