© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 731
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities

    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
    لاس
    1.58
     informazioni
    1.49
    ات
    1.49
     πρώ
    1.48
     antiguas
    1.48
    ি
    1.43
     wykony
    1.41
     pasukan
    1.41
     mú
    1.41
    м
    1.40
    POSITIVE LOGITS
     proactive
    1.51
    <0xD8>
    1.49
     reduction
    1.48
     motorised
    1.48
     deleterious
    1.44
     societal
    1.37
     docile
    1.37
    ონ
    1.37
     fungicides
    1.37
    𝙩
    1.36
    Activations Density 0.315%

    No Known Activations