© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15100
    Prev
    Next
    INDEX
    Explanations

    money to too bankrupt space flyers stupid old shed June

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

    existential dread and intensity

    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_31_width_16k_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
     truly
    0.52
     zelfs
    0.52
     tzv
    0.48
    ⌔
    0.46
     récent
    0.45
    釭
    0.45
     ڕۆ
    0.44
    ἲ
    0.44
     doub
    0.43
     `'
    0.43
    POSITIVE LOGITS
     fucking
    0.73
    shit
    0.70
     weird
    0.68
     shitty
    0.66
     shit
    0.64
     freaking
    0.64
    weird
    0.63
    fuck
    0.62
     fucked
    0.62
    aaaaaaaa
    0.59
    Activations Density 0.620%

    No Known Activations