© 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. 45461
    Prev
    Next
    INDEX
    Explanations

    punctuation and general separators

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

    formal client or weird authors

    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
    ुर
    0.45
     unsafe
    0.42
     compone
    0.42
     carri
    0.42
     musst
    0.40
     collapsed
    0.40
    .
    0.40
     Component
    0.40
     allowed
    0.39
     Bxe
    0.39
    POSITIVE LOGITS
    િર
    0.47
     ঘোষিত
    0.47
     বিপ্লবী
    0.46
    റിയി
    0.45
    λάβ
    0.45
    漂亮的
    0.45
    👔
    0.44
    加快
    0.43
     মধুর
    0.43
    政治
    0.43
    Activations Density 0.000%

    No Known Activations