© 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. 208767
    Prev
    Next
    INDEX
    Explanations

    aged nine

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

    respirator or singularity

    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
     (_
    0.50
     avion
    0.50
     hton
    0.49
     paese
    0.49
    ことが多い
    0.49
    owneri
    0.48
     vid
    0.48
     amaz
    0.48
     vea
    0.47
     informe
    0.46
    POSITIVE LOGITS
     घूम
    0.49
     Arzneim
    0.48
     मैथमेटिक्स
    0.46
    染色
    0.46
     麻
    0.46
    麻
    0.46
    门
    0.45
    婶
    0.45
    dominal
    0.45
     Син
    0.45
    Activations Density 0.001%

    No Known Activations