© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1444
    Prev
    Next
    INDEX
    Explanations

    lack of or conditional statements

    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
     protections
    1.07
     nedenle
    0.92
     ọ
    0.91
    *
    0.90
    —
    0.87
     bakan
    0.86
     colère
    0.86
     mengapa
    0.83
     pasukan
    0.83
    *.
    0.82
    POSITIVE LOGITS
     upto
    1.45
     caters
    1.35
     totally
    1.31
     atleast
    1.31
    totally
    1.29
     irrespective
    1.24
     Totally
    1.23
     attains
    1.21
     basically
    1.18
    Totally
    1.17
    Activations Density 0.320%

    No Known Activations