© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 9061
    Prev
    Next
    INDEX
    Explanations

    row and pages definitions

    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_9_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
     MMS
    1.17
     Grafton
    1.14
    alertDialog
    1.10
    Ironically
    1.10
    omeres
    1.08
    𝐬
    1.07
     Bartlett
    1.06
    wine
    1.05
     LCS
    1.04
     Genes
    1.03
    POSITIVE LOGITS
    ্যাম
    1.32
     ৭০
    1.30
     forskellige
    1.24
    Saludos
    1.23
    Precio
    1.23
    Nicht
    1.22
     manipulator
    1.21
     möjlig
    1.20
    𝑖
    1.19
    會
    1.19
    Activations Density 0.000%

    No Known Activations