© 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. 165075
    Prev
    Next
    INDEX
    Explanations

    Beckham, real income, experienced, defining

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

    combined then followed by an action

    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
    جي
    0.50
    目录下
    0.48
    codingPath
    0.47
    Ᏸ
    0.46
    谟
    0.46
    アナログ
    0.46
    楽
    0.46
    مي
    0.45
    Basis
    0.45
    amerikanischer
    0.45
    POSITIVE LOGITS
     stitched
    0.49
     কিন্ত
    0.46
     일부
    0.45
     _
    0.45
     slowdown
    0.44
     blended
    0.44
     knitted
    0.44
     Rica
    0.43
     intent
    0.42
     sustained
    0.42
    Activations Density 0.000%

    No Known Activations