© 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. 145240
    Prev
    Next
    INDEX
    Explanations

    multilingual content

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

    Paper Scissors balance power

    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
     undesired
    0.43
     verbess
    0.41
    itación
    0.39
     Airtel
    0.39
     inlet
    0.39
     aunt
    0.38
    淑
    0.38
    荫
    0.38
     Brig
    0.38
    up
    0.38
    POSITIVE LOGITS
     शूटिंग
    0.53
     σχέ
    0.50
     producteurs
    0.50
    ですが
    0.49
     कार्यकर्ते
    0.49
     limite
    0.48
     आहोत
    0.48
     ਤ
    0.47
     personnages
    0.47
     filme
    0.47
    Activations Density 0.000%

    No Known Activations