© 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. 123294
    Prev
    Next
    INDEX
    Explanations

    high and low values

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

    introduces a contrast

    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
     Mem
    0.54
     Políticas
    0.49
     skipped
    0.47
     Vlad
    0.46
    ك
    0.46
     ou
    0.45
     reconstru
    0.45
     Rep
    0.44
     Mors
    0.43
     patiently
    0.43
    POSITIVE LOGITS
    ardonnay
    0.59
    磅
    0.52
    伸縮
    0.52
    iorari
    0.51
    rneğin
    0.50
    limiting
    0.49
    तमंद
    0.49
    蓝色
    0.47
    agaman
    0.47
    蓝
    0.46
    Activations Density 0.001%

    No Known Activations