© 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. 1885
    Prev
    Next
    INDEX
    Explanations

    bail Zimmerman bonds bailout

    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
    凊
    0.42
     respecter
    0.39
     ideally
    0.38
    Biscuit
    0.38
     моду
    0.37
    fabrik
    0.37
     Reproduced
    0.36
     użytk
    0.36
    䒱
    0.36
    语气
    0.35
    POSITIVE LOGITS
     bail
    0.63
     Ba
    0.59
     ba
    0.55
     Bail
    0.55
    Ba
    0.53
    bail
    0.50
     bailout
    0.48
     BA
    0.48
     bonds
    0.47
     baile
    0.46
    Activations Density 0.002%

    No Known Activations