© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 732
    Prev
    Next
    INDEX
    Explanations

    algorithmic training

    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_17_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
     précédent
    1.13
     /
    1.05
    /
    1.04
     ситуацию
    1.03
     Gedanken
    1.01
     Antwort
    0.99
    ituation
    0.96
    /(
    0.95
     afirma
    0.92
     circunst
    0.92
    POSITIVE LOGITS
    独特的
    1.54
     distinctive
    1.41
     interiors
    1.31
    配色
    1.27
     structured
    1.26
     lunghezza
    1.25
    此外
    1.25
    幅広い
    1.24
     intricate
    1.22
    独特
    1.22
    Activations Density 0.570%

    No Known Activations