© 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. 164024
    Prev
    Next
    INDEX
    Explanations

    Addition and related words

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

    text generation for specific audiences

    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
    ки
    0.61
    чём
    0.52
    щем
    0.49
    masına
    0.47
    та
    0.46
    ват
    0.45
     吴
    0.45
     symbolized
    0.45
     gestellt
    0.45
    йдёт
    0.44
    POSITIVE LOGITS
    鎳
    0.45
     Addition
    0.45
    Zitat
    0.45
    ├──
    0.43
    itors
    0.43
    aling
    0.42
    rps
    0.42
    azón
    0.42
    Carter
    0.42
    f
    0.41
    Activations Density 0.000%

    No Known Activations