© 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. 60191
    Prev
    Next
    INDEX
    Explanations

    right hand, three posters

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

    binary classification (yes/no, fraud)

    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
     nunca
    0.52
     компен
    0.51
     infus
    0.50
     artr
    0.50
     пан
    0.50
     ಇದ್ದ
    0.49
    넬
    0.49
    સા
    0.48
     шах
    0.48
     tratados
    0.48
    POSITIVE LOGITS
    victory
    0.46
     victory
    0.44
     Curriculum
    0.44
    Employment
    0.43
    earned
    0.42
    APPING
    0.42
    סף
    0.41
    amalla
    0.41
    ="")
    0.41
     phí
    0.40
    Activations Density 0.000%

    No Known Activations