© 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. 128469
    Prev
    Next
    INDEX
    Explanations

    gambling site, amounts paid, Memorial Day

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

    continuation of high ratios

    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
    at
    0.52
    s
    0.48
     subsets
    0.47
     Before
    0.46
     Somewhat
    0.44
     Stick
    0.44
    ه
    0.43
    ের
    0.43
    dor
    0.43
     Simultaneously
    0.43
    POSITIVE LOGITS
     kaise
    0.55
     lavoratori
    0.50
     başarılı
    0.49
    !”,
    0.49
     xấu
    0.49
     inspiración
    0.48
     ecz
    0.48
    !”.
    0.48
     fenomeni
    0.48
     کیسے
    0.48
    Activations Density 0.000%

    No Known Activations