© 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. 53410
    Prev
    Next
    INDEX
    Explanations

    production; resource; witnesses; case; thing

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

    subjective qualities and judgments

    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
    le
    0.55
    l
    0.55
    na
    0.54
    <div>
    0.51
     name
    0.51
    la
    0.50
    component
    0.50
     journeys
    0.50
    li
    0.49
    り
    0.48
    POSITIVE LOGITS
     hMut
    0.49
    堈
    0.49
    㧕
    0.48
    ˦
    0.47
     melibatkan
    0.47
     سعی
    0.46
     করিয়াছেন
    0.45
    ত্তম
    0.45
    BURSE
    0.45
    alleng
    0.44
    Activations Density 0.000%

    No Known Activations