© 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. 56075
    Prev
    Next
    INDEX
    Explanations

    production figures or names

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

    validation logic

    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
    逞
    0.58
     terdapat
    0.55
    かれて
    0.52
     घरात
    0.51
    いますが
    0.50
     vea
    0.48
     repas
    0.48
    Рас
    0.47
     osk
    0.47
     suro
    0.47
    POSITIVE LOGITS
     mockery
    0.48
    enstein
    0.45
    జా
    0.44
    ोत्सव
    0.43
     Context
    0.43
     \|\
    0.43
     Poem
    0.42
    ஸ
    0.42
     Trauma
    0.42
     Shayari
    0.42
    Activations Density 0.001%

    No Known Activations