© 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. 6520
    Prev
    Next
    INDEX
    Explanations

    command line instructions

    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
     hoặc
    1.22
     or
    1.21
     или
    1.20
     nebo
    1.17
     ή
    1.12
     atau
    1.11
    或
    1.11
    หรือ
    1.11
     或
    1.10
    或是
    1.09
    POSITIVE LOGITS
    Use
    0.81
    Query
    0.69
    Using
    0.68
     другой
    0.68
    Whatever
    0.67
    Direct
    0.65
     മറ്റൊരു
    0.64
     Use
    0.63
    Case
    0.60
    Online
    0.59
    Activations Density 0.053%

    No Known Activations