© 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. 942
    Prev
    Next
    INDEX
    Explanations

    get Predicate / find Primes

    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
     epistem
    1.32
     indie
    1.22
     herpes
    1.22
    ❇
    1.20
     cyborg
    1.20
     psychedelic
    1.19
     trink
    1.18
     neoliberal
    1.18
    😑
    1.17
    💟
    1.16
    POSITIVE LOGITS
    Re
    1.49
    Un
    1.48
    Min
    1.43
    Real
    1.40
    Sub
    1.39
    Start
    1.38
    Base
    1.37
    Comp
    1.36
    Res
    1.34
    Not
    1.33
    Activations Density 0.223%

    No Known Activations