© 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. 234959
    Prev
    Next
    INDEX
    Explanations

    futures or generation planning

    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
     "
    0.50
    as
    0.50
    ate
    0.48
    stev
    0.47
    an
    0.46
    evident
    0.45
    r
    0.44
    aft
    0.42
     Section
    0.42
    short
    0.42
    POSITIVE LOGITS
     anál
    0.62
    Você
    0.57
     dwRes
    0.55
    𝗘
    0.55
     músicos
    0.53
    ཁ
    0.52
    ಪೆ
    0.52
     শহরে
    0.51
    Fant
    0.51
    你也
    0.51
    Activations Density 0.000%

    No Known Activations