© 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. 168075
    Prev
    Next
    INDEX
    Explanations

    travel and money advice

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

    Mistral AI models

    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
     과
    0.54
    ней
    0.48
    '*
    0.47
    вина
    0.45
    asing
    0.44
     ክፍል
    0.44
    ysis
    0.44
     регистрации
    0.43
     разнови
    0.42
     да
    0.42
    POSITIVE LOGITS
    تهم
    0.56
     Fever
    0.50
    ض
    0.47
    لک
    0.47
     Dummy
    0.47
    рифт
    0.47
    copic
    0.46
     Mixed
    0.45
    ت
    0.45
    س
    0.45
    Activations Density 0.000%

    No Known Activations