© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4050
    Prev
    Next
    INDEX
    Explanations

    etc. and similar conjunctions

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

    lists and bullet points

    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
    。",
    0.57
    .):
    0.55
    냐면
    0.49
    .',
    0.45
    .,
    0.44
    .");
    0.43
    .",
    0.42
     '',
    0.42
     എന്നാണ്
    0.42
    。)
    0.42
    POSITIVE LOGITS
     ইত্যাদি
    0.61
     など
    0.60
    等等
    0.59
     тощо
    0.59
     Etc
    0.55
     etc
    0.51
     etcétera
    0.46
     इत्यादि
    0.45
     including
    0.45
     INCLUDING
    0.45
    Activations Density 0.133%

    No Known Activations