© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12398
    Prev
    Next
    INDEX
    Explanations

    few-shot examples

    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_7_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
    plied
    2.80
    ედ
    2.56
    guesses
    2.55
    ἲ
    2.55
    気の
    2.44
    ᱽ
    2.42
    ἰ
    2.38
    atique
    2.31
    fö
    2.30
     configFile
    2.27
    POSITIVE LOGITS
    বাহ
    2.67
    बीन
    2.48
     camas
    2.42
    َات
    2.38
     renal
    2.32
    িক
    2.29
    بع
    2.27
    ്രി
    2.26
     suffis
    2.23
    =&
    2.21
    Activations Density 0.014%

    No Known Activations