© 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. 30312
    Prev
    Next
    INDEX
    Explanations

    seen much

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

    Every followed by instance

    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
    配置
    0.53
    ه
    0.46
    Key
    0.45
    服务的
    0.45
    *=
    0.44
     services
    0.43
     duty
    0.43
    Pov
    0.42
    क
    0.41
    gruntled
    0.41
    POSITIVE LOGITS
     स्वातंत्र्य
    0.49
     स्वातंत्र
    0.49
    педії
    0.47
     jederzeit
    0.46
     Randomized
    0.46
     Numpy
    0.45
     universitaria
    0.45
     Minkowski
    0.45
    غات
    0.45
     உலகின்
    0.44
    Activations Density 0.000%

    No Known Activations