© 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. 197780
    Prev
    Next
    INDEX
    Explanations

    compatibility , comparer , paying, credit

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

    foster parents / study titles

    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
    泻
    0.48
    newLine
    0.47
    h
    0.47
    squig
    0.47
    agamanam
    0.46
    ল
    0.46
    𝑮
    0.45
    Offset
    0.44
    czek
    0.44
     করাতে
    0.43
    POSITIVE LOGITS
    宣言
    0.44
     اعتبار
    0.42
     compar
    0.42
    用に
    0.41
     comparability
    0.40
     rings
    0.39
     comparer
    0.39
     clarifications
    0.39
    們
    0.39
     patri
    0.39
    Activations Density 0.003%

    No Known Activations