© 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. 6221
    Prev
    Next
    INDEX
    Explanations

    slurred speech

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

    especially, special, origin, relation

    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
    0.19
    ר
    0.17
    𝙖
    0.17
    𝘢
    0.16
     bilingual
    0.15
     две
    0.15
    েও
    0.15
    𝖾
    0.15
    ﺭ
    0.15
    ৌম
    0.14
    POSITIVE LOGITS
     plufieurs
    0.14
     prefque
    0.14
    .​
    0.14
     angenommen
    0.13
    ».
    0.13
     kammam
    0.13
    コレート
    0.13
     Ogni
    0.13
    ®.
    0.13
    .“
    0.13
    Activations Density 10.246%

    No Known Activations