© 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. 39845
    Prev
    Next
    INDEX
    Explanations

    continuation or subsequent steps

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

    subsequence and remainder

    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
     흰
    0.39
    艶
    0.36
     mềm
    0.36
     τρόπο
    0.36
     প্রার্থ
    0.35
    렘
    0.35
     αντί
    0.35
    萫
    0.35
     selam
    0.35
     ピンク
    0.34
    POSITIVE LOGITS
     Subsequent
    0.49
     остальные
    0.49
     나머지
    0.49
     나머
    0.48
     Other
    0.47
     остальных
    0.46
     Thereafter
    0.46
     Gradually
    0.44
    后续
    0.44
     Others
    0.42
    Activations Density 0.020%

    No Known Activations