© 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. 21612
    Prev
    Next
    INDEX
    Explanations

    buy the, based on, move it

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

    code, github, factorio

    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
     only
    0.43
     mankind
    0.41
    .
    0.41
     clientele
    0.40
     rewards
    0.40
     chances
    0.39
     beneficio
    0.38
     aren
    0.38
     הראש
    0.38
     suggest
    0.37
    POSITIVE LOGITS
    这两个
    0.51
    錒
    0.47
     машиналарын
    0.46
     तालि
    0.46
    江苏
    0.45
     intraven
    0.45
     तसेच
    0.45
    binicons
    0.44
    yester
    0.43
     reiniciar
    0.43
    Activations Density 0.000%

    No Known Activations