© 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. 249149
    Prev
    Next
    INDEX
    Explanations

    purchased between

    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
     ఇతర
    0.60
     個人
    0.56
     ､
    0.55
     其他
    0.53
     தம்
    0.48
     ಇತರ
    0.48
     ආරක්ෂ
    0.45
     こんな
    0.45
     వ్యవ
    0.44
     किस्म
    0.44
    POSITIVE LOGITS
    '
    0.58
    为
    0.55
     sebagai
    0.52
     menjadi
    0.52
     dengan
    0.52
     avec
    0.51
     bởi
    0.50
    มัน
    0.49
     parfaite
    0.48
    通过
    0.48
    Activations Density 0.000%

    No Known Activations