© 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. 162984
    Prev
    Next
    INDEX
    Explanations

    world, hymn, sandpaper, machine

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

    customer support and research

    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
     взе
    0.49
     jednotliv
    0.49
    uttab
    0.48
    of
    0.47
    avoir
    0.47
     };
    0.47
    }_
    0.46
    jeu
    0.46
    viewModel
    0.45
    
    0.45
    POSITIVE LOGITS
    ళ్
    0.43
    瑀
    0.43
    исто
    0.43
     också
    0.43
     সেখান
    0.42
     từ
    0.41
     rainbows
    0.41
    到时候
    0.40
    ckså
    0.40
    Atlanta
    0.40
    Activations Density 0.001%

    No Known Activations