© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4412
    Prev
    Next
    INDEX
    Explanations

    Harry Potter universe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     Bridgeport
    0.83
     গার্ম
    0.83
     TEX
    0.78
     urban
    0.76
     도시
    0.73
     CDK
    0.72
    渚
    0.71
    滨
    0.71
     trucker
    0.71
     కార్
    0.71
    POSITIVE LOGITS
     Hogwarts
    2.30
     Harry
    2.17
    Harry
    2.07
     wizards
    1.97
     wizard
    1.82
     Potter
    1.81
    harry
    1.78
     Wizard
    1.77
     Rowling
    1.75
     Vold
    1.74
    Activations Density 0.063%

    No Known Activations