© 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. 7729
    Prev
    Next
    INDEX
    Explanations

    foreign language characters or names

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

    domains requiring projects

    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
    ρός
    0.47
    öhn
    0.46
     chimneys
    0.46
     rostr
    0.45
    ূলে
    0.44
     milled
    0.44
     heirloom
    0.44
    렜
    0.44
     roost
    0.43
     intramuscular
    0.43
    POSITIVE LOGITS
     ପ୍ର
    0.51
     अनन्या
    0.49
    ]，
    0.49
     なん
    0.46
     Shao
    0.45
     ባህ
    0.45
     ነገር
    0.45
    Paulo
    0.45
     チャ
    0.45
    댜
    0.45
    Activations Density 0.000%

    No Known Activations