© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47075
    Prev
    Next
    INDEX
    Explanations

    negative sentiment intensifiers

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

    raise an eyebrow

    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_262k_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
     presente
    0.48
    INPUT
    0.47
     Aufgaben
    0.46
    i
    0.45
    II
    0.44
    某一
    0.44
     펼
    0.44
    İR
    0.43
     задач
    0.42
     fenómeno
    0.42
    POSITIVE LOGITS
     fucking
    0.52
     dodgy
    0.52
     shitty
    0.52
     disgusting
    0.51
     fucked
    0.46
     banging
    0.46
     KFC
    0.45
     merda
    0.45
     crappy
    0.44
     bloody
    0.43
    Activations Density 0.000%

    No Known Activations