© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    every word start with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     It
    1.29
     C
    1.24
    ch
    1.16
    C
    1.10
     P
    1.09
    ode
    1.04
     II
    1.03
     A
    1.03
     ...
    1.02
     T
    1.01
    POSITIVE LOGITS
     ünivers
    1.74
     sektör
    1.63
     diğer
    1.62
     komunitas
    1.62
     berbasis
    1.59
     psicología
    1.56
    行业
    1.56
     multidis
    1.55
     stakeholder
    1.54
    MethodBeat
    1.53
    Activations Density 0.002%

    No Known Activations