© 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. 65270
    Prev
    Next
    INDEX
    Explanations

    phone numbers and code flags

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

    multilingual text types

    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
    I
    0.53
    ogene
    0.48
     kaj
    0.48
    itecture
    0.47
     Edmund
    0.45
    ief
    0.45
     Mohr
    0.44
     tiba
    0.44
     verdient
    0.44
    㗽
    0.44
    POSITIVE LOGITS
    <0x80>
    0.54
    ാണ
    0.54
    ین
    0.53
     vestiges
    0.53
     ポリ
    0.53
     ሌሎች
    0.52
     사용하여
    0.51
    ಾ
    0.51
     ፕሮ
    0.50
     نیاز
    0.50
    Activations Density 0.000%

    No Known Activations