© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2219
    Prev
    Next
    INDEX
    Explanations

    harmful stereotypes, encryption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     wiped
    1.33
    豉
    1.26
     generational
    1.25
     tecnológicas
    1.24
     gestion
    1.24
     jubil
    1.23
     Gestión
    1.22
    励
    1.22
     automática
    1.21
     automatique
    1.21
    POSITIVE LOGITS
    triangle
    1.84
     triangle
    1.81
     equilateral
    1.78
    Triangle
    1.71
    三角形
    1.69
     triangles
    1.68
    angle
    1.68
    angles
    1.64
    Angles
    1.62
    perimeter
    1.60
    Activations Density 0.429%

    No Known Activations