© 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. 133763
    Prev
    Next
    INDEX
    Explanations

    which the

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

    control and agency

    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
    пи
    0.55
    el
    0.48
    judice
    0.46
    elung
    0.46
    }]$,
    0.46
    hematic
    0.44
    RN
    0.43
    Progress
    0.43
    🇵
    0.43
     nové
    0.43
    POSITIVE LOGITS
     ਤਾਂ
    0.51
     ಯಾವಾಗ
    0.51
     ۋە
    0.45
     प्रस्तु
    0.44
     πρώτη
    0.43
     όταν
    0.43
     नेहमी
    0.42
    ோ
    0.42
     فونٹ
    0.42
    StoredKeys
    0.42
    Activations Density 0.001%

    No Known Activations