© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4501
    Prev
    Next
    INDEX
    Explanations

    Bill followed by a surname

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

    billions

    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
    rades
    0.39
     VAS
    0.38
    ects
    0.37
    㚘
    0.37
    सीएम
    0.37
     Decorated
    0.37
    কানিক্যাল
    0.36
    㑯
    0.36
     Cancer
    0.36
     उमेद
    0.36
    POSITIVE LOGITS
    ennium
    0.49
    ions
    0.46
     bores
    0.46
     unhappy
    0.45
     нен
    0.42
     Marriott
    0.42
     jumpers
    0.41
    avista
    0.41
    jump
    0.41
     jumper
    0.41
    Activations Density 0.007%

    No Known Activations