© 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. 19401
    Prev
    Next
    INDEX
    Explanations

    structured data keys

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

    structured definitions

    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
    如果你
    0.40
    其
    0.40
     pagination
    0.39
     sources
    0.39
    ="">
    0.39
    いく
    0.39
    }).
    0.38
    继
    0.38
     mezzo
    0.37
     signature
    0.37
    POSITIVE LOGITS
    がありますが
    0.42
     거고
    0.41
     Avis
    0.39
    {},
    0.38
     কিন্তু
    0.38
     אבל
    0.37
     університету
    0.37
    há
    0.36
    ={},
    0.36
    Ṕ
    0.36
    Activations Density 0.009%

    No Known Activations