© 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. 5600
    Prev
    Next
    INDEX
    Explanations

    when followed by a subject

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

    when introducing conditions or processes

    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
     بأن
    0.66
    𝙚
    0.64
     主要
    0.63
     sikre
    0.63
     चोपड़ा
    0.63
    ون
    0.62
     لأن
    0.62
    gesetz
    0.60
     정도로
    0.60
    <unused2179>
    0.59
    POSITIVE LOGITS
    soever
    0.82
    때
    0.82
    when
    0.74
    러
    0.69
     you
    0.68
    к
    0.68
     asked
    0.67
     जेव्हा
    0.66
     llegue
    0.66
    ី
    0.66
    Activations Density 0.286%

    No Known Activations