© 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. 111255
    Prev
    Next
    INDEX
    Explanations

    search terms and outcomes

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

    loan applications

    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
     می‌توانید
    0.53
    ვ
    0.46
    gelijk
    0.45
    medieval
    0.45
     sociales
    0.45
     jaren
    0.44
    শেষ
    0.44
    膂
    0.44
    ﻛ
    0.44
    გი
    0.43
    POSITIVE LOGITS
     CUP
    0.55
     PP
    0.53
     ECO
    0.52
     HA
    0.50
     IH
    0.50
     FF
    0.49
     GAO
    0.49
     HOPE
    0.49
     YY
    0.48
     Hertz
    0.48
    Activations Density 0.001%

    No Known Activations