© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 83952
    Prev
    Next
    INDEX
    Explanations

    often soften, usually inherit

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

    referencing user's prior input

    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
    αρ
    0.47
     কাগ
    0.45
    頴
    0.43
    implemented
    0.43
    syllabus
    0.43
    Unsere
    0.43
    フィルム
    0.42
    PLEASE
    0.42
     possano
    0.42
    最初に
    0.42
    POSITIVE LOGITS
     👋
    0.50
    sez
    0.48
     🎉
    0.47
     timestamp
    0.45
     intrigue
    0.45
     Uygh
    0.44
     👀
    0.43
     😏
    0.42
     reprieve
    0.41
     unwelcome
    0.41
    Activations Density 0.000%

    No Known Activations