© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3408
    Prev
    Next
    INDEX
    Explanations

    pooling or still

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

    still pool

    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
     LD
    0.42
    মিত
    0.40
     Rout
    0.38
    प्रभात
    0.38
    Tap
    0.37
    inescence
    0.37
     subroutine
    0.37
    鵠
    0.37
     Constructs
    0.36
    MNumber
    0.36
    POSITIVE LOGITS
     pool
    0.74
     pools
    0.65
    pool
    0.65
    Pool
    0.63
     Pool
    0.63
     puls
    0.60
    POOL
    0.58
     pulse
    0.55
     Pools
    0.54
    プール
    0.53
    Activations Density 0.000%

    No Known Activations