© 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. 7-GEMMASCOPE-2-RES-16K
    4. 584
    Prev
    Next
    INDEX
    Explanations

    stating AI's helpful and harmless purpose

    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
     údaje
    1.68
    nętr
    1.61
     aşağıdaki
    1.61
     Einstellungen
    1.57
     objRequest
    1.56
    欳
    1.55
     prüfen
    1.54
     filóso
    1.54
     şöyle
    1.54
     filoz
    1.53
    POSITIVE LOGITS
     consecutive
    1.39
    h
    1.01
    x
    0.92
    th
    0.92
     long
    0.88
     uninterrupted
    0.87
     their
    0.86
     both
    0.84
     upset
    0.83
     interrupted
    0.83
    Activations Density 1.065%

    No Known Activations