© 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. 73539
    Prev
    Next
    INDEX
    Explanations

    diverse concepts and specific entities

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

    enrichment, comparison, droplet growth, encryption

    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
     ٻ
    0.48
     ልጅ
    0.48
     puoi
    0.46
     sensible
    0.43
     possiamo
    0.43
     mumkin
    0.42
     blancs
    0.42
     nejs
    0.41
     možno
    0.41
    ᱯ
    0.41
    POSITIVE LOGITS
     вследствие
    0.48
    售后
    0.42
    തോടെ
    0.42
     Webber
    0.42
     Industria
    0.42
    的网络
    0.41
    இந்நிலையில்
    0.40
     Alcoholic
    0.40
    ி
    0.40
     Injuries
    0.40
    Activations Density 0.002%

    No Known Activations