© 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. 266
    Prev
    Next
    INDEX
    Explanations

    finding image galleries

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

    הַ (Ha) for "the"

    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
     coarsely
    0.45
    stå
    0.43
    stände
    0.39
     certificat
    0.39
    Millan
    0.38
     =~
    0.38
    ständen
    0.38
    ündet
    0.38
    粗
    0.37
    )」
    0.37
    POSITIVE LOGITS
    ils
    0.44
    de
    0.40
     grafts
    0.40
    wick
    0.39
     De
    0.39
     gonna
    0.39
    PPP
    0.39
     wicked
    0.38
     guna
    0.38
     de
    0.38
    Activations Density 0.005%

    No Known Activations