© 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. 166035
    Prev
    Next
    INDEX
    Explanations

    really, truly, genuinely

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

    actions and processes

    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
     TOG
    0.45
    둥
    0.43
    😣
    0.43
    비스
    0.42
     DISCUSSION
    0.42
    uming
    0.42
    뺀
    0.42
    팅
    0.41
    ichia
    0.41
    getMessage
    0.40
    POSITIVE LOGITS
     वाकई
    0.50
     मनोरंजन
    0.49
     সত্যিই
    0.48
     ক্ষুধা
    0.46
     bû
    0.45
     naprawdę
    0.45
    人都
    0.45
     gerçekten
    0.45
     davvero
    0.44
     théor
    0.44
    Activations Density 0.001%

    No Known Activations