© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4076
    Prev
    Next
    INDEX
    Explanations

    templates, schemas, specifications

    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
    arge
    1.55
    arged
    1.32
    iga
    1.30
    र
    1.28
    ulos
    1.24
    Responder
    1.22
    sock
    1.21
    mage
    1.20
    u
    1.19
    opolar
    1.18
    POSITIVE LOGITS
     výstav
    1.67
     buku
    1.64
     knih
    1.61
     Ausbildung
    1.55
     volled
    1.52
     kitap
    1.51
     vok
    1.50
     책
    1.50
     knj
    1.49
    దర్శ
    1.47
    Activations Density 0.310%

    No Known Activations