© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 67312
    Prev
    Next
    INDEX
    Explanations

    treating displacementaccepting a propositionchoices give outcomesthat can lead

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

    describing actions, states, or 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
    也没有
    0.49
    国
    0.49
     Invention
    0.49
    詞
    0.43
    也沒有
    0.43
     Deck
    0.42
    の世界
    0.42
    拟
    0.41
     deck
    0.41
    скую
    0.41
    POSITIVE LOGITS
     Phaser
    0.49
     systém
    0.45
     footballers
    0.45
    agem
    0.45
     moisturizer
    0.45
     ajuda
    0.44
     klanten
    0.44
     saraf
    0.43
     ద్వారా
    0.43
    ți
    0.43
    Activations Density 0.002%

    No Known Activations