© 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. 160992
    Prev
    Next
    INDEX
    Explanations

    company, Monaco, project, rental, night

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

    adventure and services

    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
     isoform
    0.53
     serotonin
    0.51
     penchant
    0.48
     estradiol
    0.47
     downregulation
    0.46
     mogul
    0.46
     cinematographer
    0.46
     ჩ
    0.46
     occuper
    0.46
     superiority
    0.45
    POSITIVE LOGITS
     佐
    0.52
    佐
    0.52
    THERS
    0.45
     Railway
    0.44
    elje
    0.44
     フォ
    0.42
     作
    0.42
    waiting
    0.42
    Railway
    0.41
     සා
    0.41
    Activations Density 0.001%

    No Known Activations