© 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. 55582
    Prev
    Next
    INDEX
    Explanations

    bloggers or lobbyists

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

    linear regression

    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
    른
    0.49
    완
    0.47
    四个
    0.45
    proposition
    0.42
     دیر
    0.41
     পাঁচটি
    0.41
    ouvrage
    0.41
    5
    0.41
    쁘
    0.40
    Japanese
    0.40
    POSITIVE LOGITS
     lobbyists
    0.51
     bloggers
    0.48
    श्मा
    0.46
     Chatterjee
    0.46
     champs
    0.46
     ड्रग
    0.45
     lobby
    0.45
     vodka
    0.44
     Lobby
    0.44
     Sinha
    0.44
    Activations Density 0.000%

    No Known Activations