© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6079
    Prev
    Next
    INDEX
    Explanations

    truly followed by positive descriptors

    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_65k_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
    AL
    1.30
    Tanggal
    1.23
     بہ
    1.10
    AP
    1.08
    POM
    1.08
    Р
    1.04
    𝐫
    1.01
    PL
    0.99
    Ť
    0.97
    WY
    0.97
    POSITIVE LOGITS
    焐
    1.10
     imposing
    1.09
     cavern
    1.07
     adequacy
    1.06
    shoe
    1.05
     referring
    1.04
     alterations
    1.04
     annihilation
    1.00
    类似
    1.00
     causas
    1.00
    Activations Density 0.002%

    No Known Activations