© 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. 135944
    Prev
    Next
    INDEX
    Explanations

    until, after, unless

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

    linked consequences

    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
    شی
    0.42
     Biden
    0.41
    augmented
    0.41
    ]
    0.41
    Biden
    0.40
    the
    0.38
    primarily
    0.38
    eringen
    0.38
    announce
    0.38
    styles
    0.38
    POSITIVE LOGITS
     হত্যা
    0.49
    뷊
    0.48
     হত্যাকা
    0.46
     被
    0.46
     cysts
    0.46
    、“
    0.44
     শারীরিক
    0.44
     hindering
    0.44
     heartbreaking
    0.43
     ভীষণ
    0.43
    Activations Density 0.000%

    No Known Activations