© 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. 52447
    Prev
    Next
    INDEX
    Explanations

    promised or predicted futures

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

    intended plans

    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
     newState
    0.39
    ఢ
    0.39
    ச
    0.39
    ृ
    0.38
    ائق
    0.38
     travels
    0.37
    ወ
    0.36
     良
    0.36
     tort
    0.35
    disamb
    0.35
    POSITIVE LOGITS
     promised
    1.61
    promised
    1.34
     predicted
    1.23
     Promised
    1.21
     previsto
    1.12
     prévue
    1.10
    predicted
    1.09
     обеща
    1.09
     предусмотре
    1.09
     prévu
    1.09
    Activations Density 0.152%

    No Known Activations