© 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. 104128
    Prev
    Next
    INDEX
    Explanations

    Umrah

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

    bolded introductory 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
    etrot
    0.51
    orage
    0.49
     gubit
    0.48
     쉬
    0.48
    に応じて
    0.46
     चिन्ह
    0.46
     ricord
    0.46
     секрета
    0.45
     disparition
    0.45
    dispatchEvent
    0.45
    POSITIVE LOGITS
    t
    0.55
    s
    0.52
     Manchester
    0.44
     Stockholm
    0.43
    j
    0.43
    ↓
    0.43
     सिन्हा
    0.42
    ta
    0.42
    UK
    0.41
    b
    0.41
    Activations Density 0.000%

    No Known Activations