© 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. 186090
    Prev
    Next
    INDEX
    Explanations

    service, return, issues, BC

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

    represents, updates, aligns

    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
    縱
    0.52
     Behör
    0.49
    ਣ
    0.48
    плення
    0.48
     देखकर
    0.45
    водства
    0.44
    وک
    0.44
     Tiro
    0.44
     Bezir
    0.44
    JUnit
    0.43
    POSITIVE LOGITS
     california
    0.46
    dc
    0.44
     spends
    0.44
     heals
    0.43
    return
    0.42
     Primarily
    0.42
    ael
    0.42
    段
    0.42
     cuidado
    0.41
     retains
    0.40
    Activations Density 0.001%

    No Known Activations