© 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. 5548
    Prev
    Next
    INDEX
    Explanations

    uses or leverages

    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
     большинства
    1.10
    /
    1.04
    เภท
    0.85
     ili
    0.84
    /-
    0.81
     многих
    0.80
     многим
    0.79
    /+
    0.78
    (:
    0.78
    itude
    0.77
    POSITIVE LOGITS
     まず
    1.22
    asks
    1.18
     hadronic
    1.18
     dismantled
    1.17
     তোলা
    1.14
     먼저
    1.14
     graphene
    1.12
     tensors
    1.12
     voxel
    1.12
     seduced
    1.12
    Activations Density 0.114%

    No Known Activations