© 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. 142152
    Prev
    Next
    INDEX
    Explanations

    managed toanalyser functionthis beachsome aremost gelatoatm withdrawal

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

    past states and actions

    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
     parmi
    0.47
     amalgamated
    0.42
     безу
    0.41
     encroachment
    0.41
     U
    0.41
    ringen
    0.41
    man
    0.41
     unspecified
    0.41
     March
    0.40
     generically
    0.39
    POSITIVE LOGITS
     FullHD
    0.51
    fireFlower
    0.50
    લ
    0.50
     それ
    0.49
    يارات
    0.49
    チーム
    0.49
    eep
    0.48
    Luckily
    0.47
    viewDidLoad
    0.47
    𝙛
    0.47
    Activations Density 0.000%

    No Known Activations