© 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. 169496
    Prev
    Next
    INDEX
    Explanations

    insider secrets

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

    talking about you and room

    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
     ד
    0.46
     ვ
    0.44
     ე
    0.43
    alámb
    0.43
    siehe
    0.42
    spě
    0.42
    腭
    0.42
     정리
    0.42
     ווא
    0.42
     מיט
    0.42
    POSITIVE LOGITS
     বোল
    0.50
     innebär
    0.49
     signifies
    0.46
    сү
    0.44
     to
    0.43
     shoppers
    0.43
     muffins
    0.43
    চৈত
    0.43
     berupa
    0.42
     medall
    0.42
    Activations Density 0.000%

    No Known Activations