© 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. 129235
    Prev
    Next
    INDEX
    Explanations

    Aramark, Sodexo, exclusive rights

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

    models, system, data, escape

    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
    İL
    0.53
    NESS
    0.52
     腕時計
    0.52
     মাথ
    0.51
    芯片
    0.51
     variabile
    0.51
    PARATION
    0.50
    𝕂
    0.50
    ATHER
    0.49
     NATIONAL
    0.49
    POSITIVE LOGITS
    avas
    0.48
    ava
    0.47
    obic
    0.45
    }]
    0.44
    java
    0.44
    ospace
    0.43
    ascape
    0.43
    accessible
    0.42
    n
    0.42
     commenting
    0.42
    Activations Density 0.001%

    No Known Activations