© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6119
    Prev
    Next
    INDEX
    Explanations

    you can

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

    essential to

    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_53_width_65k_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
    오
    0.41
    속
    0.40
     insured
    0.39
    출
    0.38
    드
    0.38
    र्
    0.38
    Ра
    0.38
     called
    0.36
    Funds
    0.36
    0.36
    POSITIVE LOGITS
     hice
    0.47
     inoltre
    0.47
     فونبټ
    0.46
     azonban
    0.46
     aisa
    0.45
     entanto
    0.45
     ähm
    0.44
     sajana
    0.43
     volna
    0.43
     tels
    0.42
    Activations Density 0.085%

    No Known Activations