© 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. 222139
    Prev
    Next
    INDEX
    Explanations

    number sequences followed by other numbers

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

    note that, store that

    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
    ándor
    0.49
     derivations
    0.47
    advers
    0.47
     предела
    0.45
    €
    0.45
     अध्ययन
    0.45
     représentant
    0.44
     сумка
    0.44
     முடிவு
    0.43
    llo
    0.43
    POSITIVE LOGITS
    OLUTION
    0.55
    ULATION
    0.51
     parseFloat
    0.43
    聁
    0.42
     Nexus
    0.42
     System
    0.42
    Mosaic
    0.42
    дою
    0.41
     Solid
    0.41
    球
    0.41
    Activations Density 0.001%

    No Known Activations