© 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. 94872
    Prev
    Next
    INDEX
    Explanations

    clinical practice, inflight service, be stored, € 40,00

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

    interpret, acknowledge situations

    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
     politič
    0.45
     bırak
    0.45
    政策
    0.44
    정책
    0.42
     güvenlik
    0.42
     theology
    0.41
    🚌
    0.41
    💾
    0.41
    思想
    0.40
    ﺴ
    0.40
    POSITIVE LOGITS
     Mushrooms
    0.53
     पुर
    0.48
     Jog
    0.47
    minton
    0.46
    ousand
    0.46
    ire
    0.46
     Headphones
    0.46
     Himalayan
    0.45
     PUBG
    0.45
     मश
    0.45
    Activations Density 0.002%

    No Known Activations