© 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. 191510
    Prev
    Next
    INDEX
    Explanations

    Jason perform

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

    self-discovery, Enumeration, quote

    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
    FEC
    0.49
    CCCCC
    0.48
    綴
    0.48
    پار
    0.46
    アイテム
    0.46
    パート
    0.46
    廼
    0.45
    ペン
    0.44
     patente
    0.44
     اقتص
    0.44
    POSITIVE LOGITS
    вью
    0.44
     motivación
    0.43
     flav
    0.42
    ếu
    0.41
     Demi
    0.41
    чку
    0.41
    ější
    0.41
     চলবে
    0.41
     disbelief
    0.40
     zelfs
    0.40
    Activations Density 0.001%

    No Known Activations