© 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. 34458
    Prev
    Next
    INDEX
    Explanations

    free or readable

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

    mathematical and temporal phrases

    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
    ម
    0.45
    שי
    0.44
    ಮಾನ
    0.44
     iyo
    0.44
    న
    0.43
    erjee
    0.42
    ////
    0.42
    SH
    0.42
     migliore
    0.42
    ोजन
    0.42
    POSITIVE LOGITS
     lectured
    0.45
     employé
    0.42
    動物
    0.41
    pictureBox
    0.40
     特許庁
    0.40
     duż
    0.40
     উদ্ভাব
    0.40
    vdash
    0.39
     خدمة
    0.39
     الحلقة
    0.39
    Activations Density 0.000%

    No Known Activations