© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1066
    Prev
    Next
    INDEX
    Explanations

    family, Google, data security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ίδα
    1.28
    atakse
    1.15
    addAction
    1.06
    〉
    1.05
    étés
    1.05
    TTLE
    1.05
    itaan
    1.03
    ourent
    1.03
    éc
    1.02
    াহিয়া
    1.00
    POSITIVE LOGITS
    ет
    1.08
     tardes
    0.99
     skim
    0.98
    ма
    0.98
     cultivo
    0.98
    েল
    0.98
     permission
    0.98
    𝚊
    0.98
     psih
    0.97
     скоро
    0.97
    Activations Density 0.000%

    No Known Activations