© 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. 95078
    Prev
    Next
    INDEX
    Explanations

    charts, tables, algorithms, information

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

    voice commands, Mars, killed

    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
    દ
    0.45
     мнение
    0.42
    લ
    0.42
    Price
    0.42
    Metallic
    0.42
    বি
    0.41
    Кар
    0.41
    :]:
    0.40
    ಗೆ
    0.40
    -])
    0.40
    POSITIVE LOGITS
    alingrad
    0.55
     breathing
    0.48
     xung
    0.47
     naut
    0.46
     läng
    0.46
     sinh
    0.45
    南京
    0.43
     rescues
    0.42
     kontakt
    0.42
     sytu
    0.42
    Activations Density 0.002%

    No Known Activations