© 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. 39445
    Prev
    Next
    INDEX
    Explanations

    days of the week and dates

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

    days and dates, weather

    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
    ﻹ
    0.46
     היו
    0.42
    愭
    0.42
    矶
    0.42
    apeutics
    0.42
    绩
    0.41
     Gabri
    0.41
     Apoll
    0.41
     көр
    0.40
     Barrington
    0.40
    POSITIVE LOGITS
    <span>
    0.40
     nad
    0.39
    ovel
    0.39
     &#
    0.39
     ]
    0.37
     NONE
    0.37
    <a>
    0.37
    (&
    0.36
     vaan
    0.36
     除
    0.36
    Activations Density 0.000%

    No Known Activations