© 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. 181467
    Prev
    Next
    INDEX
    Explanations

    for or after phrases

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

    clothing, forever, off, sculpted

    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
    煒
    0.49
    ্দ
    0.46
    ፑ
    0.46
    羵
    0.46
    ᆫ
    0.45
    뭡
    0.43
     yǒu
    0.43
     nft
    0.42
    聾
    0.42
     reiterate
    0.42
    POSITIVE LOGITS
    for
    0.54
     for
    0.47
    yielding
    0.46
    agency
    0.45
     Lombardi
    0.43
     Europeo
    0.43
    untuk
    0.42
     ไว้
    0.42
    ities
    0.41
    Austria
    0.41
    Activations Density 0.000%

    No Known Activations