© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46703
    Prev
    Next
    INDEX
    Explanations

    descriptive qualifiers of people/situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    郏
    0.45
    ակ
    0.44
    ڈ
    0.44
    ільки
    0.43
    ließen
    0.43
     ডেস্ক
    0.43
    ቡ
    0.43
    ailed
    0.42
    ोली
    0.42
     ή
    0.42
    POSITIVE LOGITS
     personalidad
    0.47
     personality
    0.45
    &
    0.44
    භාව
    0.44
     presencia
    0.43
     business
    0.41
     family
    0.40
     cumpr
    0.40
     ع
    0.40
     difficult
    0.40
    Activations Density 0.014%

    No Known Activations